Rubber quality inspection method and apparatus, medium, device, and program product

Abstract

The present application relates to the technical field of rubber manufacturing. Disclosed in the embodiments are a rubber quality inspection method and apparatus, a medium, a device, and a program product. The method comprises: according to first tensile strength data and second tensile strength data, obtaining similarity data and a root mean square error value of the tensile strength data; and, according to the similarity data and the root mean square error value, obtaining an accuracy of verification, so as to complete quality inspection on target rubber. The present application directly compares the tensile strength data of the target rubber with the tensile strength data of standard rubber in the same time period, thereby avoiding interferences from multiple factors; the accuracy of verification is decomposed into the similarity and the root mean square error, and the root mean square error is used to measure the degree of data dispersion, thereby representing the difference between a measured value and an actual value; coupling the similarity and the root mean square error can obtain a higher degree of accuracy of the tensile strength of the target rubber with respect to the tensile strength of the standard rubber, which serves as the accuracy of verification, thereby improving the level of quality inspection for the target rubber.

Description

A rubber quality inspection method, device, medium, equipment and program product Technical Field

[0001] The present application relates to the field of rubber manufacturing technology, and in particular to a rubber quality inspection method, device, medium, equipment and program product. Background Art

[0002] Rubber products are typically used under certain external forces, requiring them to possess certain physical and mechanical properties. The most important of these properties is tensile strength, a crucial physical performance indicator for determining rubber quality. Existing techniques rely on multiple measurements to determine the measurement uncertainty of rubber tensile strength and analyze the impact of various factors on tensile strength. This consumes considerable time and results in low stability in the measurement data, leading to subpar quality inspections of rubber based on tensile strength.

[0003] Summary of the Invention

[0004] The main purpose of this application is to provide a rubber quality inspection method, device, medium, equipment and program product, aiming to solve the problem of low level of quality inspection of rubber based on tensile strength in the prior art.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a rubber quality inspection method, comprising the following steps:

[0007] respectively obtaining first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within the target time period;

[0008] Obtaining similarity data of the tensile strength data according to the first tensile strength data and the second tensile strength data;

[0009] Obtaining a root mean square error value of the tensile strength data according to the first tensile strength data and the second tensile strength data;

[0010] Based on the similarity data and the root mean square error value, the calibration accuracy is obtained to complete the quality inspection of the target rubber.

[0011] By obtaining the tensile strength data of the target rubber and directly comparing it with the tensile strength data of the standard rubber in the same time period, the interference of multiple factors is avoided, and the accuracy of the calibration is decomposed into similarity and root mean square error. The root mean square error is used to measure the discreteness of the data and characterize the gap between the measured value and the true value of each data. By coupling the similarity and the root mean square error, a more accurate accuracy of the tensile strength of the target rubber relative to the tensile strength of the standard rubber is obtained as the calibration accuracy, thereby completing the improvement of the quality inspection level of the target rubber.

[0012] In a possible implementation of the first aspect, before respectively obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period, the rubber quality inspection method further includes:

[0013] According to the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber, first tensile strength data of the target rubber in the target time period and second tensile strength data of the standard rubber in the target time period are obtained respectively.

[0014] The sample data is presented more clearly in the form of time series data, and the required first tensile strength data can be directly determined from the first tensile strength time series data, and the second tensile strength data at the same target time can be determined from the constructed second tensile strength time series data.

[0015] In a possible implementation of the first aspect, before obtaining first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within the target time period based on the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber, the rubber quality inspection method further includes:

[0016] According to the tensile strength data of the target rubber and the standard rubber in several time periods, first tensile strength time series data of the target rubber and second tensile strength time series data of the standard rubber are constructed.

[0017] Since the tensile strength data is acquired over a period of time, the tensile strength time series data can be constructed in advance, that is, arranged according to time and corresponding tensile strength.

[0018] In a possible implementation of the first aspect, after constructing first tensile strength time series data of the target rubber and second tensile strength time series data of the standard rubber based on tensile strength data of the target rubber and the standard rubber over several time periods, the rubber quality inspection method further includes:

[0019] Constructing a rubber tensile strength database based on the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber;

[0020] According to the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber, first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within a target time period are obtained respectively, including:

[0021] In the rubber tensile strength database, first tensile strength data of the target rubber in a target time period and second tensile strength data of the standard rubber in a target time period are obtained respectively according to first tensile strength time series data of the target rubber and second tensile strength time series data of the standard rubber.

[0022] In order to make the storage and retrieval of various data more convenient and improve the efficiency of rubber quality inspection, a rubber tensile strength database is built in advance, and the time series data are stored in the database. When applying, the corresponding data can be called from the database as needed.

[0023] In a possible implementation of the first aspect, after obtaining a root mean square error value of the tensile strength data based on the first tensile strength data and the second tensile strength data, the rubber quality inspection method further includes:

[0024] If the root mean square error value is greater than the first threshold, returning to the step of respectively obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period, until the root mean square error value is no greater than the first threshold, thereby obtaining a target root mean square error value;

[0025] Based on the similarity data and the root mean square error value, the calibration accuracy is obtained to complete the quality inspection of the target rubber, including:

[0026] According to the similarity data and the target root mean square error value, the calibration accuracy is obtained to complete the quality inspection of the target rubber.

[0027] The first threshold is set based on experience. For example, it can be set to 5 under normal circumstances. That is, when the root mean square error is not greater than 5, the data is usable. If it exceeds 5, it is necessary to remeasure until it does not exceed 5. This value is used as the final root mean square error value, that is, the target root mean square error value.

[0028] In a possible implementation of the first aspect, obtaining verification accuracy according to the similarity data and the root mean square error value includes:

[0029] The verification accuracy is obtained based on the similarity data, the root mean square error value, and the weight ratio of the similarity data to the root mean square error value.

[0030] In order to make the coupled data more accurate, the proportion of each part of the data in the coupled data is determined according to its importance. Since the root mean square error is the standard for measuring the difference between the detection value and the true value, the similarity data is mainly used, and its proportion is greater than the root mean square error value.

[0031] In a possible implementation of the first aspect, after obtaining first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within the target time period, the rubber quality inspection method further includes:

[0032] Obtaining a tensile strength line graph in a target time period according to the first tensile strength data and the second tensile strength data;

[0033] Obtaining similarity data of the tensile strength data according to the first tensile strength data and the second tensile strength data, including:

[0034] According to the tensile strength line graph in the target time period, similarity data of the tensile strength data is obtained.

[0035] The numerical value and changing trend of tensile strength are more clearly reflected in the form of a broken line graph. The discrete degree of data can also be observed more clearly through the broken line graph. Some data that are far dispersed from the broken line corresponding to standard rubber can be obviously determined to be invalid data and can be eliminated or re-measured.

[0036] In a possible implementation of the first aspect, obtaining similarity data of tensile strength data according to a tensile strength line graph in a target time period includes:

[0037] According to the tensile strength broken line graph in the target time period, the overlap degree of the tensile strength broken lines of the target rubber and the standard rubber in the target time period is obtained;

[0038] According to the degree of overlap, similarity data of the tensile strength data is obtained.

[0039] Similarity measures the degree of similarity between two data points. When obtaining similarity using a line graph, the similarity between lines actually measures the degree of overlap between the two lines. Similar to similarity, the overlap is also a number between 0 and 1. The obtained overlap can be directly used as the similarity data for the tensile strength data. In this way, the complex similarity problem is transformed into a simple linear overlap problem.

[0040] In a possible implementation of the first aspect, obtaining similarity data of tensile strength data according to a tensile strength line graph in a target time period includes:

[0041] According to the tensile strength line graph in the target time period, the difference between the first tensile strength data and the second tensile strength data at each time point is obtained;

[0042] constructing a tensile strength difference graph in a target time period according to the difference between the first tensile strength data and the second tensile strength data at each time point;

[0043] Perform linear fitting on the points on the tensile strength difference graph under the target time period, and obtain the horizontality of the fitting line as the similarity data of the tensile strength data.

[0044] The idea behind this method is to simplify the two objects used for similarity comparison into one object, and use this object to directly represent the similarity. In this embodiment, the difference is used as a measure. The specific idea is: when the two broken lines completely overlap, the values ​​on the two broken lines corresponding to each horizontal coordinate are the same, and the difference is 0. The difference map is composed of all points with a difference of 0. The ideal state is a horizontal line. When the two broken lines do not overlap, the difference is definitely not equal to 0, which is equivalent to the points representing the difference dynamically changing within a certain range above and below 0. If the ideal state with a difference of 0 is regarded as a horizontal plane, then the actual state is that this horizontal plane fluctuates. Therefore, all points on the difference map are linearly fitted, and a continuous line is used to represent this fluctuation. The degree of fluctuation can be called horizontality, which can be used as the basis for similarity. For example, the greater the fluctuation, the worse the horizontality, and the lower the similarity. It should be noted that the degree of fluctuation here needs to be normalized, and the data is mapped to the range of 0-1 corresponding to the similarity. Usually, similarity is measured from the positive direction, so the similarity here should actually be 1 minus the actual similarity.

[0045] In a possible implementation of the first aspect, performing linear fitting on points on a tensile strength difference graph within a target time period to obtain the horizontality of the fitting line as the similarity data of the tensile strength data includes:

[0046] Perform linear fitting on the points on the tensile strength difference graph under the target time period to obtain a fitting line;

[0047] If the fitting line satisfies the invalidation condition, the process returns to the step of obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period, respectively, until the fitting line no longer satisfies the invalidation condition, and the horizontality of the fitting line is obtained as the similarity data of the tensile strength data; wherein the invalidation condition is that the horizontality of the fitting line is 1 and the corresponding difference is not zero.

[0048] When using differences as the basis for similarity, a special case may arise: the difference between the first tensile strength data of the target rubber and the second tensile strength data of the standard rubber is the same on every horizontal axis. In other words, the two lines on the image have identical trends, with only a difference in height. Therefore, a linear fit of the resulting difference will also result in a straight line. In this case, compared to the ideal straight line with a difference of 0, the two parallel lines cannot produce the result of similarity measured by horizontality in this application. Although this situation is almost impossible to occur, it can be eliminated through a judgment process during the fully computer-implemented process. This judgment is based on an invalid condition: that is, if the horizontality of the fitted line is 1, indicating that the line has no fluctuations, but the corresponding difference is not 0, indicating that the target rubber is not completely consistent with the standard rubber. Therefore, this situation is invalid and the initial step can be returned to the original step for re-measurement.

[0049] In a possible implementation of the first aspect, after obtaining a tensile strength line graph in a target time period based on the first tensile strength data and the second tensile strength data, the rubber quality inspection method further includes:

[0050] In the tensile strength line graph for the target time period, if the difference between the first tensile strength data and the second tensile strength data at each time point is greater than a second threshold, returning to the step of respectively obtaining the first tensile strength data of the target rubber for the target time period and the second tensile strength data of the standard rubber for the target time period until the difference is no greater than the second threshold, thereby obtaining the target tensile strength line graph for the target time period;

[0051] According to the tensile strength line graph in the target time period, the similarity data of the tensile strength data is obtained, including:

[0052] According to the target tensile strength line graph in the target time period, similarity data of the tensile strength data is obtained.

[0053] A threshold is set to control invalid data that is far away from the center. That is, if the difference between the corresponding data on the two broken lines is very large when viewed from the same horizontal axis, of course, the difference here is the absolute value. If the value exceeds the second threshold, it means that the data difference is large. It may be that the measurement is wrong or the measurement is interfered by special circumstances. You can return to the initial measurement acquisition step to re-measure the various tensile strength data, and finally obtain a difference that does not exceed the second threshold. At this time, the line graph is the target tensile strength line graph under the standard time period.

[0054] In a second aspect, an embodiment of the present application provides a rubber quality inspection device, comprising:

[0055] a first obtaining module, the first obtaining module being used to respectively obtain first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within the target time period;

[0056] a second obtaining module, the second obtaining module being configured to obtain similarity data of the tensile strength data according to the first tensile strength data and the second tensile strength data;

[0057] a third obtaining module, the third obtaining module being configured to obtain a root mean square error value of the tensile strength data according to the first tensile strength data and the second tensile strength data;

[0058] The verification module is used to obtain the verification accuracy based on the similarity data and the root mean square error value to complete the quality inspection of the target rubber.

[0059] In a third aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, the rubber quality inspection method provided in any one of the first aspects above is implemented.

[0060] In a fourth aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, wherein:

[0061] Memory is used to store computer programs;

[0062] The processor is used to load and execute a computer program so as to enable the electronic device to execute the rubber quality inspection method provided in any one of the first aspects above.

[0063] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed, is used to execute the rubber quality inspection method provided in any one of the first aspects above.

[0064] Compared with the prior art, the present invention has the following advantages:

[0065] The present invention provides a rubber quality inspection method, apparatus, medium, device, and program product. The method comprises: obtaining first tensile strength data of a target rubber within a target time period and second tensile strength data of a standard rubber within the target time period; obtaining similarity data of the tensile strength data based on the first and second tensile strength data; obtaining a root mean square error (RMSE) value of the tensile strength data based on the first and second tensile strength data; and obtaining a calibration accuracy based on the similarity data and the RMS error value to complete the quality inspection of the target rubber. The present invention obtains the tensile strength data of the target rubber and directly compares it with the tensile strength data of the standard rubber within the same time period, avoiding interference from multiple factors. The calibration accuracy is decomposed into similarity and RMS error. The RMS error is used to measure the degree of data dispersion and characterize the difference between the measured value and the true value of each data. By coupling the similarity and RMS error, a more accurate accuracy of the tensile strength of the target rubber relative to the tensile strength of the standard rubber is obtained as the calibration accuracy, thereby improving the quality inspection level of the target rubber. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] FIG1 is a schematic diagram of the structure of an electronic device in a hardware operating environment according to an embodiment of the present application;

[0067] FIG2 is a schematic flow chart of a rubber quality inspection method provided in an embodiment of the present application;

[0068] FIG3 is a schematic flow chart of a rubber quality inspection method according to an embodiment of the present application;

[0069] FIG4 is a schematic diagram of a tensile strength broken line graph in the rubber quality inspection method provided in an embodiment of the present application;

[0070] FIG5 is a schematic diagram of a module of a rubber quality inspection device provided in an embodiment of the present application;

[0071] Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory. DETAILED DESCRIPTION

[0072] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0073] The main solution of the embodiment of the present application is: obtaining first tensile strength data of the target rubber within the target time period and second tensile strength data of the standard rubber within the target time period respectively; obtaining similarity data of the tensile strength data based on the first tensile strength data and the second tensile strength data; obtaining a root mean square error value of the tensile strength data based on the first tensile strength data and the second tensile strength data; and obtaining calibration accuracy based on the similarity data and the root mean square error value to complete the quality inspection of the target rubber.

[0074] Rubber products are typically used under certain external forces, requiring them to possess certain physical and mechanical properties. The most important of these properties is tensile strength, a crucial physical property indicator for determining rubber quality. Existing technologies, such as those based on GB / T528-2009, "Rubber, vulcanized or thermoplastic — Determination of tensile stress-strain properties," and JJF1059.1-2012, "Evaluation and Expression of Uncertainty in Measurement," determine a mathematical model for rubber tensile strength, analyze the primary sources of measurement uncertainty, and calculate each source to determine the measurement uncertainty. This approach consumes significant time and results in low stability in the measured data, leading to subpar quality inspections of rubber based on tensile strength.

[0075] Other methods, such as the patent application with publication number CN108768656A, describe a hash algorithm for data verification that has a simple structure and fast computational speed and can be implemented in various programming languages. The algorithm comprises the following steps: S1, reading in the data to be processed for data verification; S2, specifying a specified word length, L, of binary data, and storing the data in groups from high to low bits according to the specified word length, L; S3, setting the initial value of the hash code using the golden section parameter; S4, setting the shift number of the hash code using the golden section parameter; S5, cyclically shifting the current hash code to the left by the shift number obtained in S4, and adding it to the data in the highest-order group in the existing data group to generate a new hash code; S6, deleting the current highest-order group of data that participated in the calculation in S5; S7, repeating S5 and S6 until all the grouped data stored in S1 are deleted. The resulting hash code is the final check value, which is used for data verification. However, this method places high demands on data accuracy and cannot determine data similarity.

[0076] Another example is the "Uncertainty Evaluation and Application Analysis of Styrene-Butadiene Rubber Tensile Strength Test Results," a publicly available document on CNKI. This study evaluated the uncertainty of styrene-butadiene rubber tensile strength test results. The results showed that the uncertainty component introduced by repeatability testing is the primary source of uncertainty in the tensile strength test results, followed by the maximum allowable error of the tensile testing machine, thickness gauge, and cutter width. Using uncertainty representation can more comprehensively and accurately reflect material quality. However, this method has limited stability and requires repeated testing to ensure data accuracy.

[0077] To this end, the present application provides a solution, which obtains the tensile strength data of the target rubber and directly compares it with the tensile strength data of the standard rubber in the same time period, avoiding the interference of multiple factors, and decomposing the accuracy of the verification into similarity and root mean square error. The root mean square error is used to measure the discreteness of the data, characterize the gap between the measured value and the true value of each data, and couple the similarity and root mean square error to obtain a more accurate accuracy of the tensile strength of the target rubber relative to the tensile strength of the standard rubber as the verification accuracy, thereby completing the improvement of the quality inspection level of the target rubber.

[0078] Referring to Figure 1, Figure 1 is a schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiment of the present application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or a stable non-volatile memory (NVM), such as at least one disk memory. The processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0079] Those skilled in the art will appreciate that the structure shown in FIG1 does not limit the electronic device and may include more or fewer components than shown, or combine certain components, or arrange components differently.

[0080] As shown in FIG1 , the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and a rubber quality inspection device.

[0081] In the electronic device shown in Figure 1, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in this application can be set in the electronic device, and the electronic device calls the rubber quality inspection device stored in the memory 105 through the processor 101 and executes the rubber quality inspection method provided in the embodiment of this application.

[0082] Referring to FIG. 2 , based on the hardware device of the aforementioned embodiment, an embodiment of the present application provides a rubber quality inspection method, comprising the following steps:

[0083] S10: obtaining first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within the target time period respectively.

[0084] During implementation, the target rubber is the rubber to be quality inspected, and the target time period is a set testing period. The tensile strength data for the target rubber within this time period is obtained, i.e., the first tensile strength data. To avoid randomness in the results, the target time period is typically set to a longer period, such as 12 or 24 hours. The standard rubber is a standard product identical to the target rubber. For example, if a model XX rubber is being inspected, the corresponding model XX standard rubber is used as a comparison to obtain the tensile strength data for the standard rubber, i.e., the second tensile strength data. This avoids the need for tedious, multi-faceted testing and assesses tensile strength based on test data. The tensile state within the time period can be directly compared with that of the standard sample, forming the basis for quality inspection.

[0085] S20: Obtaining similarity data of the tensile strength data according to the first tensile strength data and the second tensile strength data.

[0086] In practice, product quality testing in this embodiment involves comparing the actual tensile strength of the rubber being tested with the standard tensile strength. The closer the comparison, the better the quality. To ensure that the actual tensile strength data used for comparison is closer to the actual value, the verification is divided into two steps. The first step verifies the similarity of the tensile strength data, comparing the first tensile strength data with the second tensile strength data to determine the similarity between the target and standard tensile strength data. The similarity is a number between 0 and 1, with a value of 0 for completely different data and 1 for completely identical data. Similarity can be measured using the degree of overlap between the data. More accurate metrics such as Euclidean distance and cosine similarity can be used.

[0087] S30: Obtaining a root mean square error value of the tensile strength data according to the first tensile strength data and the second tensile strength data.

[0088] In the specific implementation process, this step is used to obtain the root mean square error, which is the square root of the ratio of the square of the deviation between the observed value and the true value and the number of observations n. In actual measurement, the number of observations n is always limited, and the true value can only be replaced by the most reliable (optimal) value. The root mean square error value RMSE is greater than or equal to 0. When it is equal to 0, each number is equal. The root mean square error is the arithmetic square root of the variance. It is used to measure the degree of discreteness of a set of numbers itself and can better reflect the actual situation of the predicted value error. The larger the root mean square error, the greater the data deviation. When the deviation is greater than a certain degree, it means that the data deviation is too large to be used. Therefore, a threshold can be set to control the root mean square error, that is:

[0089] After obtaining a root mean square error value of the tensile strength data based on the first tensile strength data and the second tensile strength data, the rubber quality inspection method further includes:

[0090] When the root mean square error value is greater than the first threshold, the process returns to the step of respectively obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period until the root mean square error value is no greater than the first threshold, thereby obtaining the target root mean square error value.

[0091] During the specific implementation process, the first threshold is set based on experience. For example, it can be set to 5 under normal circumstances. That is, when the root mean square error is not greater than 5, the data can be used. If it exceeds 5, it is necessary to remeasure until it does not exceed 5, and then use it as the final root mean square error value, that is, the target root mean square error value.

[0092] Based on the above steps, the calibration accuracy is obtained according to the similarity data and the root mean square error value to complete the quality inspection of the target rubber, including:

[0093] According to the similarity data and the target root mean square error value, the calibration accuracy is obtained to complete the quality inspection of the target rubber.

[0094] S40: Obtaining calibration accuracy based on the similarity data and the root mean square error value to complete the quality inspection of the target rubber.

[0095] In the specific implementation process, after the verification is decomposed into two parts, the final inspection needs to return to the whole, so the two parts of data need to be coupled. The coupled data is actually a number between 0 and 1, which is used to measure the accuracy of the first tensile strength data relative to the second tensile strength data. This accuracy can be regarded as the accuracy of the verification. According to this accuracy, the quality inspection of the target rubber can be achieved. For example, according to the experience of setting the evaluation interval, if the verification accuracy reaches 85% or more, the rubber quality can be regarded as qualified and good, and if it is less than 60%, the rubber quality can be regarded as unqualified.

[0096] In one embodiment, obtaining verification accuracy based on similarity data and a root mean square error value includes:

[0097] The verification accuracy is obtained based on the similarity data, the root mean square error value, and the weight ratio of the similarity data to the root mean square error value.

[0098] In the specific implementation process, in order to make the coupled data more accurate, the proportion of each part of the data in the coupled data is determined according to its importance. Since the root mean square error is the standard for measuring the difference between the detection value and the true value, the similarity data is mainly used, and its proportion is greater than the root mean square error value. For example: Z = A*80+B*20, where Z represents the verification accuracy, A represents the similarity data, and B represents the root mean square error value. The full proportion is 1, that is, 100%. The above formula is distributed with 80 and 20, and the result of Z is directly the numerical part of the percentage data.

[0099] In this embodiment, by obtaining the tensile strength data of the target rubber and directly comparing it with the tensile strength data of the standard rubber in the same time period, interference from multiple factors is avoided, and the accuracy of the verification is decomposed into similarity and root mean square error. The root mean square error is used to measure the discreteness of the data and characterize the gap between the measured value and the true value of each data. By coupling the similarity and the root mean square error, a more accurate accuracy of the tensile strength of the target rubber relative to the tensile strength of the standard rubber is obtained as the verification accuracy, thereby completing the improvement of the quality inspection level of the target rubber.

[0100] In one embodiment, before respectively obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period, the rubber quality inspection method further includes:

[0101] According to the tensile strength data of the target rubber and the standard rubber in several time periods, first tensile strength time series data of the target rubber and second tensile strength time series data of the standard rubber are constructed.

[0102] In the specific implementation process, since the tensile strength data is obtained over a period of time, the tensile strength time series data can be constructed in advance, that is, arranged according to time and corresponding tensile strength. For example, the 24-hour tensile strength time series data S of the target rubber is selected. t , where S represents tensile strength and t represents hours, ranging from 1 to 24, t = 1, 2…24. Select the standard rubber 24-hour tensile strength time series data T t , where T represents the standard tensile strength, t represents hours, ranging from 1 to 24, t=1,2…24, S t As shown in Table 1 and Table 2 below, T t As shown in Table 3 and Table 4 below, they are:

[0103] Table 1 Sample time series data of target rubber 1-12 hour tensile strength S t

[0104] Table 2 Sample time series data of target rubber 12-24 hour tensile strength S t

[0105] Table 3 Sample time series data of standard rubber 1-12 hour tensile strength T t

[0106] Table 4 Sample time series data of standard rubber 12-24 hour tensile strength T t

[0107] According to the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber, first tensile strength data of the target rubber in the target time period and second tensile strength data of the standard rubber in the target time period are obtained respectively.

[0108] In the specific implementation, the sample data is presented more clearly in the form of time series data. The required first tensile strength data can then be directly determined from the first tensile strength time series data, and the corresponding second tensile strength data at the same target time can be determined from the constructed second tensile strength time series data. Since the standard rubber is fixed as the comparison data for the same type of rubber, a larger portion of its data can be obtained. For example, if the second tensile strength time series data is 120 hours, the target rubber can be selected from 12, 24, or 48 hours within the 120-hour range, and the corresponding portion can be directly extracted from the second tensile strength time series data.

[0109] In one embodiment, the present application provides an implementation method for measuring similarity based on cosine similarity. The cosine value cos(θ) of the cosine similarity between the 24-hour tensile strength data of the target rubber and the 24-hour tensile strength data of the standard rubber is calculated. The cosine value needs to be greater than 0 and less than 1. The closer the cosine value is to 1, the more similar the tensile strength of the target rubber and the standard rubber are. The calculation formula is as follows:

[0110] For example, taking the data from Tables 1 to 4, with t = 1, we obtain the target rubber tensile strength S1 = 68.53 and the standard rubber tensile strength T1 = 66.64. Substituting the data from Tables 1 to 4 into the formula, we can calculate the cosine similarity between the target and standard rubber tensile strengths: cos(θ) = 0.9996329.

[0111] Calculate the root mean square error (RMSE) between the target rubber tensile strength and the standard rubber tensile strength using the following formula:

[0112] Substituting the data in Tables 1 to 4 into the formula for calculation, it can be obtained that the root mean square error value of the target rubber tensile strength and the standard rubber tensile strength is RMSE = 2.9805. The root mean square error value is greater than 5. Return to step 1 and re-measure the rubber tensile strength data.

[0113] Calculate the accuracy of the target rubber tensile strength measurement data, taking the cosine similarity accounting for 80% and the root mean square error accounting for 20% as an example: Z = cos(θ)*80+(5-RMSE) / 5*20

[0114] Z represents the calibration accuracy, cos(θ) represents the cosine similarity, and RMSE represents the root mean square error. Substituting the above results into the formula for calculation, the target rubber tensile strength measurement data accuracy Z = 88.048798%.

[0115] In one embodiment, after constructing first tensile strength time series data of the target rubber and second tensile strength time series data of the standard rubber based on tensile strength data of the target rubber and the standard rubber over several time periods, the rubber quality inspection method further includes:

[0116] A rubber tensile strength database is constructed based on the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber.

[0117] In the specific implementation process, as shown in Figure 3, in order to make the storage and call of various data more convenient and improve the efficiency of rubber quality inspection, a rubber tensile strength database is constructed in advance, and the time series data are stored in the database. When applied, the corresponding data can be called from the database as needed.

[0118] Based on the aforementioned steps, first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within a target time period are obtained according to the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber, respectively, including:

[0119] In the rubber tensile strength database, first tensile strength data of the target rubber in a target time period and second tensile strength data of the standard rubber in a target time period are obtained respectively according to first tensile strength time series data of the target rubber and second tensile strength time series data of the standard rubber.

[0120] In one embodiment, after obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period, the rubber quality inspection method further includes:

[0121] A tensile strength line graph in a target time period is obtained according to the first tensile strength data and the second tensile strength data.

[0122] In the specific implementation process, the tensile strength value and change trend are more clearly reflected in the form of a broken line graph, as shown in Figure 4. The broken line graph can also more clearly observe the degree of data dispersion. Some data that are far dispersed from the broken line corresponding to the standard rubber can be clearly determined to be invalid data and can be discarded or re-measured. That is, after obtaining the tensile strength broken line graph for the target time period based on the first tensile strength data and the second tensile strength data, the rubber quality inspection method further includes:

[0123] In the tensile strength line graph for the target time period, if the difference between the first tensile strength data and the second tensile strength data at each time point is greater than the second threshold, the process returns to the step of respectively obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period until the difference is no greater than the second threshold, thereby obtaining the target tensile strength line graph for the target time period.

[0124] In the specific implementation process, a threshold is set to control invalid data that is far away from the center. That is, if the difference between the data corresponding to the two broken lines is very large when viewed from the same horizontal axis, of course, the difference here is the absolute value. If the value exceeds the second threshold, it means that the data difference is large, which may be due to measurement errors or interference from special circumstances. The initial measurement acquisition step can be returned to re-measure the various tensile strength data, and finally a difference that does not exceed the second threshold is obtained. At this time, the broken line graph is the target tensile strength broken line graph under the standard time period.

[0125] Based on the above steps, similarity data of tensile strength data is obtained according to the tensile strength line graph in the target time period, including:

[0126] According to the target tensile strength line graph in the target time period, similarity data of the tensile strength data is obtained.

[0127] Based on the aforementioned step of obtaining the broken line graph, obtaining similarity data of the tensile strength data according to the first tensile strength data and the second tensile strength data includes:

[0128] According to the tensile strength line graph in the target time period, similarity data of the tensile strength data is obtained.

[0129] Specifically, based on the tensile strength line graph in the target time period, similarity data of tensile strength data is obtained, including:

[0130] According to the tensile strength broken line graph in the target time period, the overlap degree of the tensile strength broken lines of the target rubber and the standard rubber in the target time period is obtained;

[0131] According to the degree of overlap, similarity data of the tensile strength data is obtained.

[0132] In practice, similarity measures the degree of similarity between two data points. When obtaining similarity using a line graph, the similarity between lines actually measures the degree of overlap between the two lines. Similar to similarity, the overlap is also a number between 0 and 1. The overlap obtained can be directly used as similarity data for tensile strength data. This transforms the complex similarity problem into a simple linear overlap problem.

[0133] In one embodiment, obtaining similarity data of tensile strength data based on a tensile strength line graph in a target time period includes:

[0134] According to the tensile strength line graph in the target time period, the difference between the first tensile strength data and the second tensile strength data at each time point is obtained;

[0135] constructing a tensile strength difference graph in a target time period according to the difference between the first tensile strength data and the second tensile strength data at each time point;

[0136] Perform linear fitting on the points on the tensile strength difference graph under the target time period, and obtain the horizontality of the fitting line as the similarity data of the tensile strength data.

[0137] In the specific implementation process, another implementation method for obtaining similarity data based on a line graph is provided. The idea of ​​this method is to simplify the two objects used for similarity comparison into one object, and use this object to directly represent the similarity situation. In this embodiment, the difference is used as a measure. The specific idea is: when the two broken lines completely overlap, the values ​​on the two broken lines corresponding to each horizontal coordinate are the same, and the difference is 0. The difference graph is composed of all points with a difference of 0. The ideal state is a horizontal line. When there is no overlap, the difference must not be equal to 0, which is equivalent to the point representing the difference dynamically changing within a certain range above and below 0. If the ideal state with a difference of 0 is regarded as a horizontal plane, then the actual state is that this horizontal plane has fluctuations. Therefore, all points on the difference graph are linearly fitted, and such fluctuations are represented by continuous lines. The degree of fluctuation can be called horizontality, which can be used as the basis for similarity. For example, the greater the fluctuation, the worse the horizontality, and the lower the similarity. It should be noted that the degree of fluctuation here needs to be normalized, and the data are mapped to the range of 0-1 corresponding to the similarity. Usually, the similarity is measured from the positive direction, so the similarity here should actually be 1 minus the actual similarity.

[0138] In one embodiment, performing linear fitting on the points on the tensile strength difference graph in the target time period to obtain the horizontality of the fitting line as the similarity data of the tensile strength data includes:

[0139] Perform linear fitting on the points on the tensile strength difference graph under the target time period to obtain a fitting line;

[0140] If the fitting line satisfies the invalidation condition, the process returns to the step of obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period, respectively, until the fitting line no longer satisfies the invalidation condition, and the horizontality of the fitting line is obtained as the similarity data of the tensile strength data; wherein the invalidation condition is that the horizontality of the fitting line is 1 and the corresponding difference is not zero.

[0141] During implementation, when using differences as the basis for similarity, a special case may arise: the difference between the first tensile strength data of the target rubber and the second tensile strength data of the standard rubber is identical on every horizontal axis. This means that the two lines on the image have identical trends, differing only in height. Therefore, a linear fit of the resulting difference will also produce a straight line. In this case, compared to the ideal straight line with a difference of 0, the two parallel lines cannot produce the result of similarity measured by horizontality in this application. While this situation is unlikely to occur, a judgment process can be used to eliminate it during a fully computer-based execution. This judgment is based on an invalid condition: that is, if the horizontality of the fitted line is 1, indicating that the line has no fluctuations, but the corresponding difference is not 0, indicating that the target rubber is not completely consistent with the standard rubber. Therefore, this case is invalid, and the initial step can be returned to the original step for re-measurement.

[0142] In other embodiments, if this is not excluded, similarity can be measured, but not based on horizontality. In this case, if the difference is stable and appears to be a horizontal line, then the difference can be measured relative to the standard deviation, that is, relative to 0. In fact, the difference is measured based on the absolute value of the difference. In other words, this difference can actually be considered a distance, that is, the distance between the target rubber and the standard rubber. The smaller the difference, the closer the target rubber is to the standard rubber.

[0143] 5 , based on the same inventive concept as in the above embodiment, the present embodiment further provides a rubber quality inspection device, which includes:

[0144] a first obtaining module, the first obtaining module being used to respectively obtain first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within the target time period;

[0145] a second obtaining module, the second obtaining module being configured to obtain similarity data of the tensile strength data according to the first tensile strength data and the second tensile strength data;

[0146] a third obtaining module, the third obtaining module being configured to obtain a root mean square error value of the tensile strength data according to the first tensile strength data and the second tensile strength data;

[0147] The verification module is used to obtain the verification accuracy based on the similarity data and the root mean square error value to complete the quality inspection of the target rubber.

[0148] Those skilled in the art should understand that the division of the various modules in the embodiment is merely a division of logical functions, and in actual application, they can be fully or partially integrated into one or more actual carriers, and these modules can all be implemented in the form of software called through a processing unit, or all be implemented in the form of hardware, or in the form of a combination of software and hardware. It should be noted that the modules in the rubber quality inspection device in this embodiment correspond one-to-one to the steps in the rubber quality inspection method in the aforementioned embodiment. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned rubber quality inspection method, and will not be repeated here.

[0149] Based on the same inventive concept as in the aforementioned embodiment, an embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer program is loaded and executed by a processor, the rubber quality inspection method provided in the embodiment of the present application is implemented.

[0150] Based on the same inventive concept as in the above embodiment, an embodiment of the present application further provides an electronic device, including a processor and a memory, wherein:

[0151] Memory is used to store computer programs;

[0152] The processor is used to load and execute a computer program so that the electronic device executes the rubber quality inspection method provided in the embodiment of the present application.

[0153] Based on the same inventive concept as in the aforementioned embodiment, an embodiment of the present application further provides a computer program product, including a computer program, which, when executed, is used to execute the rubber quality inspection method provided in the embodiment of the present application.

[0154] In some embodiments, the computer-readable storage medium may be a memory device such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface mount memory, optical disk, or CD-ROM; or various devices including any one or any combination of the above memories. The computer may be various computing devices including smart terminals and servers.

[0155] In some embodiments, executable instructions may be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0156] As an example, executable instructions may, but need not, correspond to a file in a file system, may be stored as part of a file that stores other programs or data, such as in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinating files (e.g., files storing one or more modules, subroutines, or code portions).

[0157] By way of example, executable instructions may be deployed to be executed on one computing device, or on multiple computing devices at one site, or on multiple computing devices distributed across multiple sites and interconnected by a communication network.

[0158] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0159] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0160] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a multimedia terminal device (which can be a mobile phone, a computer, a television receiver, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0161] In summary, the present application provides a rubber quality inspection method, apparatus, medium, equipment, and program product. The method includes: obtaining first tensile strength data of a target rubber within a target time period and second tensile strength data of a standard rubber within a target time period; obtaining similarity data of the tensile strength data based on the first tensile strength data and the second tensile strength data; obtaining a root mean square error (RMSE) value of the tensile strength data based on the first tensile strength data and the second tensile strength data; and obtaining a calibration accuracy based on the similarity data and the RMS error value to complete the quality inspection of the target rubber. The present application obtains the tensile strength data of the target rubber and directly compares it with the tensile strength data of the standard rubber within the same time period, avoiding interference from multiple factors. The calibration accuracy is decomposed into similarity and RMS error. The RMS error is used to measure the degree of data dispersion and characterize the difference between the measured value and the true value of each data. The similarity and RMS error are coupled to obtain a more accurate accuracy of the tensile strength of the target rubber relative to the tensile strength of the standard rubber as the calibration accuracy, thereby improving the quality inspection level of the target rubber.

[0162] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A rubber quality inspection method, characterized in that: The following steps are involved: Respectively obtaining first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within a target time period; wherein the first tensile strength data and the second tensile strength data are data arranged based on a time series; Obtaining similarity data of tensile strength data according to the first tensile strength data and the second tensile strength data; Obtaining a root mean square error value of the tensile strength data according to the first tensile strength data and the second tensile strength data; The verification accuracy is obtained according to the similarity data and the root mean square error value to complete the quality inspection of the target rubber.

2. The rubber quality inspection method according to claim 1, characterized in that: Before respectively obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period, the rubber quality inspection method further includes: According to the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber, first tensile strength data of the target rubber in a target time period and second tensile strength data of the standard rubber in a target time period are obtained respectively.

3. The rubber quality inspection method according to claim 2, characterized in that: Before respectively obtaining the first tensile strength data of the target rubber within a target time period and the second tensile strength data of the standard rubber within a target time period according to the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber, the rubber quality inspection method further comprises: According to the tensile strength data of the target rubber and the standard rubber in several time periods, first tensile strength time series data of the target rubber and second tensile strength time series data of the standard rubber are constructed.

4. The rubber quality inspection method according to claim 3, characterized in that: After constructing the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber according to the tensile strength data of the target rubber and the standard rubber in several time periods, the rubber quality inspection method further includes: Constructing a rubber tensile strength database according to the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber; The method of obtaining first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within a target time period respectively according to the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber comprises: In the rubber tensile strength database, first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within a target time period are respectively obtained according to the first tensile strength time series data of the target rubber and the second tensile strength time series data of the standard rubber.

5. The rubber quality inspection method according to claim 1, characterized in that: After obtaining the root mean square error value of the tensile strength data according to the first tensile strength data and the second tensile strength data, the rubber quality inspection method further includes: In the case where the root mean square error value is greater than the first threshold, returning to the step of respectively obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period, until the root mean square error value is no greater than the first threshold, and obtaining a target root mean square error value; The obtaining of the calibration accuracy according to the similarity data and the root mean square error value to complete the quality inspection of the target rubber includes: The verification accuracy is obtained according to the similarity data and the target root mean square error value to complete the quality inspection of the target rubber.

6. The rubber quality inspection method according to claim 1, characterized in that: The obtaining of the verification accuracy according to the similarity data and the root mean square error value includes: The verification accuracy is obtained according to the similarity data, the root mean square error value, and a weight ratio of the similarity data to the root mean square error value.

7. The rubber quality inspection method according to claim 1, characterized in that: After respectively obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period, the rubber quality inspection method further comprises: Obtaining a tensile strength line graph in the target time period according to the first tensile strength data and the second tensile strength data; The obtaining similarity data of tensile strength data according to the first tensile strength data and the second tensile strength data comprises: According to the tensile strength line graph in the target time period, similarity data of the tensile strength data is obtained.

8. The rubber quality inspection method according to claim 7, characterized in that: The obtaining similarity data of tensile strength data according to the tensile strength line graph in the target time period includes: According to the tensile strength broken line graph in the target time period, obtaining the overlap degree of the tensile strength broken lines of the target rubber and the standard rubber in the target time period; According to the overlap degree, similarity data of the tensile strength data is obtained.

9. The rubber quality inspection method according to claim 7, characterized in that: The obtaining similarity data of tensile strength data according to the tensile strength line graph in the target time period includes: According to the tensile strength line graph in the target time period, obtaining the difference between the first tensile strength data and the second tensile strength data at each time point; constructing a tensile strength difference graph in the target time period according to the difference between the first tensile strength data and the second tensile strength data at each time point; The points on the tensile strength difference graph under the target time period are linearly fitted to obtain the simulated The horizontality of the combined lines is used as the similarity data of the tensile strength data.

10. The rubber quality inspection method according to claim 9, characterized in that: The linear fitting of the points on the tensile strength difference graph under the target time period to obtain the horizontality of the fitting line as the similarity data of the tensile strength data includes: Performing linear fitting on the points on the tensile strength difference graph under the target time period to obtain a fitting line; When the fitting line satisfies the invalid condition, the step of respectively obtaining the first tensile strength data of the target rubber within the target time period and the second tensile strength data of the standard rubber within the target time period is returned until the fitting line does not satisfy the invalid condition, and the horizontality of the fitting line is obtained as the similarity data of the tensile strength data; wherein the invalid condition is that the horizontality of the fitting line is 1 and the corresponding difference is not zero.

11. The rubber quality inspection method according to claim 7, characterized in that: After obtaining the tensile strength line graph in the target time period according to the first tensile strength data and the second tensile strength data, the rubber quality inspection method further includes: In the tensile strength line graph in the target time period, when the difference between the first tensile strength data and the second tensile strength data at each time point is greater than a second threshold, returning to the step of respectively obtaining the first tensile strength data of the target rubber in the target time period and the second tensile strength data of the standard rubber in the target time period, until the difference is no greater than the second threshold, and obtaining the target tensile strength line graph in the target time period; The obtaining similarity data of tensile strength data according to the tensile strength line graph in the target time period includes: According to the target tensile strength line graph in the target time period, similarity data of the tensile strength data is obtained.

12. A rubber quality inspection device, characterized in that: include: A first obtaining module, the first obtaining module is used to respectively obtain first tensile strength data of the target rubber within a target time period and second tensile strength data of the standard rubber within the target time period; That In the embodiment, the first tensile strength data and the second tensile strength data are data arranged based on a time series; a second obtaining module, the second obtaining module being used to obtain similarity data of tensile strength data according to the first tensile strength data and the second tensile strength data; a third obtaining module, the third obtaining module being used to obtain a root mean square error value of the tensile strength data according to the first tensile strength data and the second tensile strength data; A verification module is used to obtain a verification accuracy according to the similarity data and the root mean square error value to complete the quality inspection of the target rubber.

13. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is loaded and executed by a processor, the rubber quality inspection method according to any one of claims 1 to 11 is implemented.

14. An electronic device, characterized in that: comprising a processor and a memory, wherein: The memory is used to store computer programs; The processor is used to load and execute the computer program so that the electronic device executes the rubber quality inspection method according to any one of claims 1 to 11.

Images