A signal line insulating material process parameter detection optimization method

Abstract

The application relates to the technical field of detection, in particular to a signal line insulating material process parameter detection optimization method, which comprises the following steps: determining the data dimension of current input data based on the sampling frequency of each environmental parameter and the correlation weight between each environmental parameter and the current process parameter to be processed; obtaining corresponding environmental parameter data from an initial environmental parameter data set as the current input data based on the data dimension of the current input data; performing fuzzification processing on the current preprocessed input data to obtain the environmental feature label corresponding to the current preprocessed input data; comparing the environmental feature label corresponding to the current preprocessed input data with the environmental feature label corresponding to the current process parameter to be processed, and adjusting the parameter value of the current process parameter to be processed based on the comparison result. The application can automatically and as accurately as possible adjust the process parameter.

Description

Technical Field

[0001] This invention relates to the field of testing technology, and in particular to a method for optimizing the testing of process parameters for signal line insulation materials. Background Technology

[0002] In today's rapidly developing electronics and information industry, signal lines, as a crucial carrier of signal transmission, directly impact the stability and reliability of the entire electronic system. Insulation materials, a vital component of signal lines, play a vital role in preventing signal leakage and providing electrical isolation; their performance is closely related to manufacturing process parameters. For example, improper temperature control during production can alter the internal structure of the insulation material, reducing its insulation performance; unreasonable pressure parameters can lead to uneven insulation thickness, affecting the stability of signal transmission. Traditional methods for detecting and adjusting the process parameters of signal line insulation materials rely heavily on manual experience and periodic sampling, resulting in low detection efficiency, delayed parameter adjustments, and difficulty adapting to complex and changing production environments. This leads to significant fluctuations in product quality and increased production costs. Therefore, researching an efficient and accurate method for optimizing the detection of process parameters for signal line insulation materials is of great significance for improving signal line quality and promoting the development of the electronics and information industry. Summary of the Invention

[0003] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows:

[0004] This invention provides a method for detecting and optimizing process parameters of signal line insulation materials, the method comprising the following steps:

[0005] S100, Obtain the environmental parameter dataset of the target spatial region within the current processing time period, as the initial environmental parameter dataset; the target spatial region is the spatial region used to prepare signal line insulation material.

[0006] S200 determines the data dimension of the current input data based on the sampling frequency of each environmental parameter and the correlation weight between each environmental parameter and the current process parameter to be processed.

[0007] S300, based on the data dimension of the current input data, obtain the corresponding environmental parameter data from the initial environmental parameter dataset as the current input data.

[0008] S400: Preprocess the current input data to obtain the preprocessed input data.

[0009] S500, the current preprocessed input data is fuzzed to obtain the environmental feature label corresponding to the current preprocessed input data; the environmental feature label includes the category label corresponding to each environmental parameter in the current preprocessed input data.

[0010] S600, compare the environmental feature labels corresponding to the current preprocessed input data with the environmental feature labels corresponding to the current process parameters to be processed, and adjust the parameter values ​​of the current process parameters to be processed based on the comparison results.

[0011] The present invention has at least the following beneficial effects:

[0012] This invention provides a method for optimizing process parameters of signal line insulation materials, comprising: acquiring an environmental parameter dataset of a target spatial region within the current processing time period as an initial environmental parameter dataset; determining the data dimension of the current input data based on the sampling frequency of each environmental parameter and the correlation weight between each environmental parameter and the current process parameter to be processed; acquiring corresponding environmental parameter data from the initial environmental parameter dataset based on the data dimension of the current input data as the current input data; preprocessing the current input data to obtain preprocessed input data; fuzzifying the preprocessed input data to obtain environmental feature labels corresponding to the preprocessed input data; comparing the environmental feature labels corresponding to the preprocessed input data with the environmental feature labels corresponding to the current process parameter to be processed, and adjusting the parameter values ​​of the current process parameter to be processed based on the comparison result. This invention, by determining the data dimension of the input data based on the sampling frequency of each environmental parameter and the correlation weight between each environmental parameter and the current process parameter to be processed, and by fuzzifying the data to obtain environmental feature labels, can automatically and as accurately as possible adjust the process parameters.

[0013] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 A flowchart illustrating a method for detecting and optimizing process parameters of signal line insulation materials, provided in an embodiment of the present invention;

[0016] Figure 2 This is a diagram illustrating how to obtain the category labels corresponding to environmental parameters. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0019] It should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processes, many of these steps can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the steps can be rearranged. A process can be terminated when its operation is complete, but it may also have additional steps not included in the figures. A process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0020] This invention provides a method for detecting and optimizing process parameters of signal line insulation materials, such as... Figure 1 As shown, the method includes the following steps:

[0021] S100: Obtain the environmental parameter dataset of the target spatial region within the current time period to be processed, and use it as the initial environmental parameter dataset.

[0022] In this embodiment of the invention, the current time period to be processed can be a time period prior to the current processing time, and the duration of the current time period to be processed can be set based on actual needs. In one illustrative embodiment, the duration of the current time period to be processed can be equal to the longest historical adjustment time interval of the process parameter. The adjustment time interval refers to the time interval for adjusting the process parameter, and the adjustment time interval of a certain process parameter can be the average adjustment time interval of that process parameter obtained based on historical data.

[0023] In this embodiment, the target spatial region is a spatial region used for preparing signal line insulation materials, specifically a production workshop for signal line insulation materials.

[0024] In this embodiment of the invention, the environmental parameters can be environmental parameters within the target space area, including temperature, humidity, and dust content, etc. Each environmental parameter can be collected by a corresponding sensor.

[0025] S200 determines the data dimension of the current input data based on the sampling frequency of each environmental parameter and the correlation weight between each environmental parameter and the current process parameter to be processed.

[0026] In this embodiment of the invention, since the sampling frequency of the sensors for each environmental parameter is different, the amount of data for each environmental parameter in the same time period is different. Therefore, it is necessary to unify the data dimension so that the processing results are as accurate as possible.

[0027] Furthermore, in this embodiment of the invention, the data dimension of the current input data satisfies the following condition:

[0028] DS=(∑ n i＝1 (d i ×k i )) / ∑ n i＝1 k i ;

[0029] Where DS represents the data dimension of the current input data, i.e., the number of data points required for each environmental parameter. i Let k be the data window size for the i-th environment parameter, where i ranges from 1 to n, n is the number of environment parameters, and k is the value of k. i The correlation weight between the i-th environmental parameter and the current process parameter to be processed.

[0030] In an embodiment of the present invention, d i =f i / f i nosie ; where f i f is the sampling frequency of the i-th environmental parameter. i nosie Let be the noise frequency of the sensor corresponding to the i-th environmental parameter.

[0031] In an embodiment of the present invention, k i The following conditions must be met:

[0032] k i =∑ m j＝1 ((X ij -AvgX)(Y ij -AvgY)) / (∑ m j＝1 (X ij -AvgX) 2 ∑ m j＝1 (Y ij -AvgY) 2 ) 1 / 2 ;

[0033] Among them, X ij Let AvgX be the j-th data point among m data points of the i-th environmental parameter collected within a historical time period, where j ranges from 1 to m. Let AvgX be the average of the m data points of the i-th environmental parameter, and Y be the... ij For X ij The corresponding acquisition time corresponds to the data value of the current process parameter to be processed. AvgY is the average value of the data values ​​of the m current process parameters to be processed corresponding to the data values ​​of the i-th environmental parameter.

[0034] In this embodiment of the invention, the duration of the historical time period is set to be longer than the duration of the current time period to be processed. The duration of the historical time period can be determined based on actual needs, as long as it includes the time period during which the current process parameters to be processed change.

[0035] In this embodiment of the invention, since the data dimension of the current input data takes into account the sampling frequency of each environmental parameter and the correlation weight between each environmental parameter and the current process parameter to be processed, the data dimension can be made as reasonable and accurate as possible.

[0036] S300, based on the data dimension of the current input data, obtain the corresponding environmental parameter data from the initial environmental parameter dataset as the current input data.

[0037] In this embodiment of the invention, for the data dimension of the current input data, the data corresponding to the environmental parameters with a small sampling frequency can be obtained from the initial environmental parameter dataset as reference data. Then, the collection time of the reference data is used as the reference time to obtain the data of other environmental parameters corresponding to each reference time, thereby obtaining the current input data.

[0038] In this embodiment of the invention, the data for other environmental parameters corresponding to each reference time can be the data for other environmental parameters corresponding to the same or closest time as the reference time. For example, for reference time a, if time a is not among the collection times of a certain environmental parameter, the data value of the time closest to time a is selected as the data value of that environmental parameter.

[0039] S400: Preprocess the current input data to obtain the preprocessed input data.

[0040] In this embodiment of the invention, in S400, the r-th data value X corresponding to each environmental parameter in the currently preprocessed input data is... r after The following conditions must be met:

[0041] X r after =α×(X) rcon )+(1-α)X r-1 after ;

[0042] X r con For the current input data that is related to X r after The corresponding data value, α is a preset coefficient, which can be an empirical value. In an illustrative embodiment, it can be a number between 0.1 and 0.3. The value of r ranges from 1 to DS.

[0043] In this embodiment of the invention, the above preprocessing enables data closer to the current processing time to play a greater role, that is, the closer the data is to the current processing time, the greater its impact on the process parameters.

[0044] S500, the current preprocessed input data is fuzzed to obtain the environmental feature label corresponding to the current preprocessed input data; the environmental feature label includes the category label corresponding to each environmental parameter in the current preprocessed input data.

[0045] Furthermore, in S500, the category label corresponding to each environmental parameter is defined by, for example... Figure 2 The steps shown are as follows:

[0046] S501, based on the value range corresponding to each environmental parameter, determine the fuzzy set corresponding to each environmental parameter.

[0047] In this embodiment of the invention, the value range corresponding to each environmental parameter can be determined based on actual conditions, for example, it can be determined based on historical environmental parameter data values ​​within the target spatial region. In this embodiment of the invention, the number of fuzzy sets can be set based on actual needs, for example, it can be set according to the operating environment parameters corresponding to the process parameters. For example, for temperature, the corresponding fuzzy sets may include fuzzy sets representing high temperature, medium temperature, and low temperature.

[0048] S502, based on the preset membership function, obtain the membership degree of each data value corresponding to the environmental parameter in the current preprocessed input data to each fuzzy set.

[0049] In this embodiment of the invention, the preset membership function can be a Gaussian function.

[0050] Those skilled in the art will know that any method for obtaining the membership degree of each data value corresponding to the environmental parameter in the current preprocessed input data to each fuzzy set based on a preset membership function is within the protection scope of this invention.

[0051] S503, based on the membership degree of each data value to each fuzzy set, determine the fuzzy set to which the dataset corresponding to the current preprocessed input data belongs, and take the category corresponding to the fuzzy set to which the dataset corresponding to the current preprocessed input data belongs as the category label corresponding to the current environment parameter.

[0052] In one embodiment of the present invention, the fuzzy set to which the dataset corresponding to the environmental parameter in the currently preprocessed input data belongs can be obtained through the following steps:

[0053] S10, Obtain the g-th fuzzy set A g The average membership degree (AvgA) of the dataset corresponding to this environmental parameter g =(1 / DS)∑ DS r＝1 β gr ; where β gr The r-th data value in the dataset corresponding to this environmental parameter belongs to fuzzy set A. g The membership degree of G. G takes values ​​from 1 to Q, where Q is the number of fuzzy sets.

[0054] S11, obtain max{AvgA1, ...,AvgA1} g , ..., AvgA Q The corresponding fuzzy set is used as the fuzzy set to which the dataset corresponding to the current preprocessed input data belongs.

[0055] In another embodiment of the present invention, the fuzzy set to which the dataset corresponding to the environmental parameter in the currently preprocessed input data belongs can be obtained through the following steps:

[0056] S20, Obtain the g-th fuzzy set A g The weighted average membership degree WAvgA of the dataset corresponding to this environmental parameter g =(1 / DS)∑ DS r＝1 W r ×β gr / ∑ DS r＝1 W r W r This represents the weight of the r-th data value in the dataset corresponding to this environmental parameter, where data values ​​closer to the current processing time have a larger weight, i.e., 0 < W1 < W2 < ... < W r <...<W DS <1.

[0057] S21, obtain max{WAvgA1, ...,WAvgA...} g , ……,WAvgA QThe corresponding fuzzy set is used as the fuzzy set to which the dataset corresponding to the current preprocessed input data belongs.

[0058] This embodiment takes into account the weight of each data value, making the fuzzy set to which each environmental parameter belongs more accurate.

[0059] In one illustrative embodiment, the environmental feature label corresponding to the preprocessed input data can be (high temperature, high humidity, low dust).

[0060] S600, compare the environmental feature labels corresponding to the current preprocessed input data with the environmental feature labels corresponding to the current process parameters to be processed, and adjust the parameter values ​​of the current process parameters to be processed based on the comparison results.

[0061] Furthermore, in S600, if at least one of the environmental feature labels corresponding to the current preprocessed input data is different from the environmental feature label corresponding to the current process parameter to be processed, the parameter value of the current process parameter to be processed is adjusted based on the environmental feature label corresponding to the current preprocessed input data.

[0062] In this embodiment of the invention, the process parameter to be processed can be any one of the process parameters involved in the generation of signal line insulation material. The process parameters involved in the generation of signal line insulation material may include raw material melting temperature, raw material extrusion temperature, raw material curing temperature, extrusion pressure, die pressure, cooling pressure, raw material ratio, etc.

[0063] In this embodiment of the invention, if at least one of the environmental feature labels corresponding to the preprocessed input data differs from the environmental feature label corresponding to the process parameter to be processed, it indicates that the environmental feature label corresponding to the preprocessed input data is different from the environmental feature label corresponding to the process parameter to be processed. This suggests that the process parameter to be processed may not be suitable for the environmental feature label corresponding to the preprocessed input data. Without adjustment, the insulation performance of the fabricated signal line may be unreasonable. Therefore, it is necessary to adjust the environmental feature label corresponding to the process parameter to be processed. Specific adjustments can be made based on actual needs. For example, the parameter value of the process parameter to be processed corresponding to the environmental feature label corresponding to the preprocessed input data can be obtained from a preset environmental feature label and process parameter correspondence table and used as the parameter value of the process parameter to be processed.

[0064] In this embodiment of the invention, each row of data in the preset environmental feature label and process parameter correspondence table includes the corresponding environmental feature label and the parameter value of the process parameter. Those skilled in the art will understand that each process parameter has a suitable environmental feature label, and the suitable environmental feature label for each process parameter can be obtained based on historical data.

[0065] Those skilled in the art will know that all process parameters can be adjusted by repeating steps S200 to S600.

[0066] This invention also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being configured to perform the method described in this invention.

[0067] This invention also provides a computer-readable storage medium storing computer-executable instructions for performing the methods described in this invention.

[0068] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0069] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting and optimizing process parameters of signal line insulation materials, characterized in that, The method includes the following steps: S100, Obtain the environmental parameter dataset of the target spatial region within the current processing time period, as the initial environmental parameter dataset; the target spatial region is the spatial region used to prepare signal line insulation material; S200 determines the data dimension of the current input data based on the sampling frequency of each environmental parameter and the correlation weight between each environmental parameter and the current process parameter to be processed; S300, based on the data dimension of the current input data, obtain the corresponding environmental parameter data from the initial environmental parameter dataset as the current input data; S400: Preprocess the current input data to obtain the preprocessed input data. S500, perform fuzzing processing on the current preprocessed input data to obtain the environmental feature label corresponding to the current preprocessed input data; the environmental feature label includes the category label corresponding to each environmental parameter in the current preprocessed input data; S600, compare the environmental feature labels corresponding to the current preprocessed input data with the environmental feature labels corresponding to the current process parameters to be processed, and adjust the parameter values ​​of the current process parameters to be processed based on the comparison result; wherein, the data dimension of the current input data satisfies the following condition: DS=(∑ n i=1 (d i ×k i )) / ∑ n i=1 k i ; Where DS represents the data dimension of the current input data, and d i Let k be the data window size for the i-th environment parameter, where i ranges from 1 to n, n is the number of environment parameters, and k is the value of k. i Let d be the association weight between the i-th environmental parameter and the current process parameter to be processed, where d i =f i / f i nosie ; where f i f is the sampling frequency of the i-th environmental parameter. i nosie The noise frequency corresponding to the sensor for the i-th environmental parameter; In S400, the r-th data value X corresponding to each environment parameter in the currently preprocessed input data. r after The following conditions must be met: X r after =α×(X r con )+(1-α)X r-1 after ; X r con For the current input data that is related to X r after The corresponding data values ​​are α, which is a preset coefficient, and r ranges from 1 to DS.

2. The method according to claim 1, characterized in that, k i The following conditions must be met: k i =∑ m j=1 ((X ij -AvgX)(Y ij -AvgY)) / (∑ m j=1 (X ij -AvgX) 2 ∑ m j=1 (Y ij -AvgY) 2 ) 1 / 2 ; Among them, X ij Let AvgX be the j-th data point among m data points of the i-th environmental parameter collected within a historical time period, where j ranges from 1 to m. Let AvgX be the average of the m data points of the i-th environmental parameter, and Y be the... ij For X ij The corresponding acquisition time corresponds to the data value of the current process parameter to be processed. AvgY is the average value of the data values ​​of the m current process parameters to be processed corresponding to the data values ​​of the i-th environmental parameter.

3. The method according to claim 1, characterized in that, The environmental parameters include temperature, humidity, and dust content.

4. The method according to claim 1, characterized in that, In S500, the category label corresponding to each environmental parameter is obtained through the following steps: S501, Based on the value range corresponding to each environmental parameter, determine the fuzzy set corresponding to each environmental parameter; S502, based on the preset membership function, obtain the membership degree of each data value corresponding to the environmental parameter in the current preprocessed input data to each fuzzy set; S503, based on the membership degree of each data value to each fuzzy set, determine the fuzzy set to which the dataset corresponding to the current preprocessed input data belongs, and take the category corresponding to the fuzzy set to which the dataset corresponding to the current preprocessed input data belongs as the category label corresponding to the current environment parameter.

5. The method according to claim 4, characterized in that, The preset membership function is a Gaussian function.

6. The method according to claim 1, characterized in that, In S600, if at least one of the environmental feature labels corresponding to the current preprocessed input data is different from the environmental feature label corresponding to the current process parameter to be processed, the parameter value of the current process parameter to be processed is adjusted based on the environmental feature label corresponding to the current preprocessed input data.

Images