Processing quality evaluation method applied to protective clothing production

Abstract

The invention relates to a processing quality evaluation method applied to protective clothing production, and the method comprises the steps: M1, in the processing process of protective clothing, obtaining the image data information of the protective clothing in real time based on a camera on a production line, and collecting the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing; and M2, on the basis of the image data information of the protective clothing, the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing, constructing a processing quality prediction model of the protective clothing, and predicting the processing quality of the protective clothing to obtain the data information of the predicted processing quality of the protective clothing. According to the invention, the protective clothing can be accurately detected, and the detection process does not need manual participation, so that the labor cost is reduced, and the production efficiency of the protective clothing is improved.

Description

Technical Field

[0001] The invention relates to the technical field of protective clothing production, and in particular to a processing quality evaluation method applied to protective clothing production. Background Art

[0002] Types of protective clothing include fire protection clothing, industrial protective clothing, medical protective clothing, military protective clothing and protective clothing for special groups. Protective clothing is mainly used in fire protection, military industry, shipbuilding, petroleum, chemical industry, painting, cleaning and disinfection, laboratories and other industries and departments. According to the protective function, it is divided into health-type protective clothing, such as radiation protection clothing, cold-proof clothing, heat-insulating clothing and antibacterial clothing; safety-type protective clothing, such as flame-retardant clothing, flame-retardant protective clothing, arc protection clothing, anti-static clothing, bullet-proof clothing, stab-proof clothing, space suits, diving suits, acid-proof clothing and insect-proof clothing; work clothes to keep the wearer hygienic, such as oil-proof clothing, dust-proof clothing and water-repellent clothing.

[0003] Therefore, in the production process of protective clothing, it is necessary to test the processing quality of protective clothing to ensure the safety of protective clothing application. The traditional protective clothing testing is to manually place the protective clothing on the testing bed, and check the protective clothing as a whole under strong light with the human eye to see if it meets the quality requirements of protective clothing. This kind of protective clothing testing is not only inefficient, but also has low detection accuracy, which will affect the quality of protective clothing and thus increase production costs. Summary of the invention

[0004] In view of the above problems, the present invention provides a processing quality evaluation method applied to the production of protective clothing, which can not only accurately detect the protective clothing, but also the detection process does not require human participation, thereby reducing labor costs and improving the production efficiency of protective clothing.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows: a processing quality evaluation method applied to the production of protective clothing, the method comprising:

[0006] M1. During the processing of protective clothing, the image data information of the protective clothing is obtained in real time based on the camera on the production line, and the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing are collected;

[0007] M2. Based on the image data information of the protective clothing, the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing, a processing quality prediction model of the protective clothing is constructed to predict the processing quality of the protective clothing, and obtain data information of the predicted processing quality of the protective clothing;

[0008] M3. Based on the predicted data information of the processing quality of the protective clothing, a processing quality parameter optimization model of the protective clothing is constructed, and the processing quality parameters of the protective clothing are optimized to obtain the parameter data information of the processing quality of the optimized protective clothing;

[0009] M4. Based on the parameter data information of the processing quality of the optimized protective clothing, the quality of the protective clothing is estimated using an improved maximum relevance minimum redundancy algorithm to obtain estimated value data information of the quality of the protective clothing.

[0010] Furthermore, in step M2, the constructing of a processing quality prediction model for protective clothing to predict the processing quality of the protective clothing includes:

[0011] M21. Based on the image data information of the protective clothing, the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing, construct a feature extraction function F of the protective clothing,

[0012]

[0013] Among them, x1 is the image data information of the protective clothing, x2 is the data information of the cutting size of the protective clothing, x3 is the data information of the sewing process parameters of the protective clothing, α1, α2 and α3 are the feature extraction constant parameters of the protective clothing, and the relevant parameters of the protective clothing are feature extracted to obtain the feature matrix data information of the relevant parameters of the protective clothing;

[0014] M22. Based on the characteristic matrix data information of the relevant parameters of the protective clothing, a contribution function Q of the relevant parameters of the protective clothing is established.

[0015]

[0016] Among them, y is the characteristic matrix data information of the relevant parameters of the protective clothing, β1, β2 and β3 are the error penalty coefficients of the protective clothing, and the contribution values ​​of the relevant parameters of the protective clothing are calculated to obtain the contribution value data information of the relevant parameters of the protective clothing;

[0017] M23. Based on the contribution value data information of the relevant parameters of the protective clothing, a processing quality prediction function W of the protective clothing is established.

[0018]

[0019] Among them, z is the contribution value data information of the relevant parameters of the protective clothing, δ1, δ2 and δ3 are the bias constant parameters of the model, and the processing quality of the protective clothing is predicted to obtain the data information of the predicted processing quality of the protective clothing.

[0020] Further, in step M23, the bias constant parameters δ1, δ2 and δ3 of the model are,

[0021]

[0022]

[0023] Among them, z is the contribution value data information of the relevant parameters of the protective clothing.

[0024] Furthermore, in step M22, the constraints of the error penalty coefficients β1, β2 and β3 of the protective clothing are:

[0025]

[0026] Further, in step M21, the constraint function f of the feature extraction constant parameters α1, α2 and α3 of the protective clothing is,

[0027]

[0028] The value range of f is (0,1).

[0029] Furthermore, the method further comprises:

[0030] M5. Based on the estimated value data information of the quality of the protective clothing, a preset threshold is set. If the estimated value of the quality of the protective clothing exceeds the preset threshold, the requirement is met and qualified protective clothing is obtained. If the estimated value of the quality of the protective clothing is less than the preset threshold, the requirement is not met and the protective clothing is discarded as unqualified.

[0031] Furthermore, in step M3, a processing quality parameter optimization model of the protective clothing is constructed, and the processing quality parameters of the protective clothing are optimized including:

[0032] M31. Based on the data information of the processing quality of the protective clothing after the prediction, a Gaussian kernel function R of the protective clothing is established.

[0033]

[0034] Among them, a is the data information of the processing quality of the protective clothing after prediction, γ1, γ2 and γ3 are weight coefficients, and the state parameter matrix of the protective clothing is characterized to obtain the state parameter matrix data information of the protective clothing;

[0035] M32. Based on the state parameter matrix data information of the protective clothing, an optimization function U of the processing quality parameters of the protective clothing is established.

[0036]

[0037] Among them, b is the state parameter matrix data information of the protective clothing, η1 and η2 are the hyperparameters of the model;

[0038] M33. Based on the optimization function U of the processing quality parameters of the protective clothing, the processing quality parameters of the protective clothing are optimized to obtain parameter data information of the processing quality of the optimized protective clothing.

[0039] Further, in step M32, the hyperparameters η1 and η2 of the model are,

[0040]

[0041] Among them, b is the state parameter matrix data information of the protective clothing.

[0042] Furthermore, in step M4, the use of the improved maximum relevance minimum redundancy algorithm to estimate the quality of the protective clothing includes:

[0043] M41. Based on the parameter data information of the processing quality of the optimized protective clothing, establish the mutual information value function G of the protective clothing,

[0044]

[0045] Among them, c is the parameter data information of the processing quality of the protective clothing after optimization, λ1 and λ2 are the correlation factors of the protective clothing, and the mutual information value of the protective clothing is calculated to obtain the mutual information value data information of the protective clothing;

[0046] M42. Based on the mutual information value data information of the protective clothing, establish a quality estimation function H of the protective clothing,

[0047]

[0048] Among them, r is the mutual information value data information of the protective clothing, ρ1, ρ2 and ρ3 are the quality determining factors of the protective clothing;

[0049] M43. Based on the quality estimation function H of the protective clothing, the quality of the protective clothing is estimated to obtain estimated value data information of the quality of the protective clothing.

[0050] Further, in step M42, the quality determining factors ρ1, ρ2 and ρ3 of the rice husk are,

[0051]

[0052] Among them, r is the mutual information value data information of the protective clothing.

[0053] The present invention has the following positive effects:

[0054] 1. The present invention predicts the processing quality of protective clothing by constructing a processing quality prediction model for protective clothing, and optimizes the processing quality parameters of protective clothing in combination with the construction of a processing quality parameter optimization model for protective clothing. Not only can the processing quality of protective clothing be accurately detected according to the image, size and sewing process parameters of the protective clothing, but the detection process does not require human participation, the degree of pollution is small, and the production quality of protective clothing is further improved.

[0055] 2. The present invention estimates the quality of protective clothing by adopting an improved maximum relevance minimum redundancy algorithm to obtain estimated value data information of the quality of protective clothing. Not only does the detection process require no human intervention, thus reducing labor costs and improving the production efficiency of protective clothing, but it also has strong robustness and is continuously optimized to improve the detection accuracy of protective clothing. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0057] Figure 2 A schematic diagram of a process for constructing a protective clothing processing quality prediction model according to the present invention;

[0058] Figure 3 A schematic diagram of the process flow of the processing quality parameter optimization model of the protective clothing of the present invention;

[0059] Figure 4 It is a flow chart of the improved maximum relevance minimum redundancy algorithm of the present invention. DETAILED DESCRIPTION

[0060] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0061] Example 1: Figure 1 As shown, a processing quality evaluation method applied to protective clothing production comprises:

[0062] M1. During the processing of protective clothing, the image data information of the protective clothing is obtained in real time based on the camera on the production line, and the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing are collected;

[0063] M2. Based on the image data information of the protective clothing, the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing, a processing quality prediction model of the protective clothing is constructed to predict the processing quality of the protective clothing, and obtain data information of the predicted processing quality of the protective clothing;

[0064] M3. Based on the predicted data information of the processing quality of the protective clothing, a processing quality parameter optimization model of the protective clothing is constructed, and the processing quality parameters of the protective clothing are optimized to obtain the parameter data information of the processing quality of the optimized protective clothing;

[0065] M4. Based on the parameter data information of the processing quality of the optimized protective clothing, the quality of the protective clothing is estimated using an improved maximum relevance minimum redundancy algorithm to obtain estimated value data information of the quality of the protective clothing.

[0066] In this embodiment, if Figure 2 As shown, in step M2, the construction of the protective clothing processing quality prediction model and the prediction of the protective clothing processing quality include:

[0067] M21. Based on the image data information of the protective clothing, the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing, construct a feature extraction function F of the protective clothing,

[0068]

[0069] Among them, x1 is the image data information of the protective clothing, x2 is the data information of the cutting size of the protective clothing, x3 is the data information of the sewing process parameters of the protective clothing, α1, α2 and α3 are the feature extraction constant parameters of the protective clothing, and the relevant parameters of the protective clothing are feature extracted to obtain the feature matrix data information of the relevant parameters of the protective clothing;

[0070] M22. Based on the characteristic matrix data information of the relevant parameters of the protective clothing, a contribution function Q of the relevant parameters of the protective clothing is established.

[0071]

[0072] Among them, y is the characteristic matrix data information of the relevant parameters of the protective clothing, β1, β2 and β3 are the error penalty coefficients of the protective clothing, and the contribution values ​​of the relevant parameters of the protective clothing are calculated to obtain the contribution value data information of the relevant parameters of the protective clothing;

[0073] M23. Based on the contribution value data information of the relevant parameters of the protective clothing, a processing quality prediction function W of the protective clothing is established.

[0074]

[0075] Among them, z is the contribution value data information of the relevant parameters of the protective clothing, δ1, δ2 and δ3 are the bias constant parameters of the model, and the processing quality of the protective clothing is predicted to obtain the data information of the predicted processing quality of the protective clothing.

[0076] In this embodiment, in step M23, the bias constant parameters δ1, δ2 and δ3 of the model are,

[0077]

[0078] Among them, z is the contribution value data information of the relevant parameters of the protective clothing.

[0079] In this embodiment, in step M22, the constraint conditions of the error penalty coefficients β1, β2 and β3 of the protective clothing are:

[0080]

[0081] In this embodiment, in step M21, the constraint function f of the feature extraction constant parameters α1, α2 and α3 of the protective clothing is,

[0082]

[0083] The value range of f is (0,1).

[0084] In this embodiment, the method further includes:

[0085] M5. Based on the estimated value data information of the quality of the protective clothing, a preset threshold is set. If the estimated value of the quality of the protective clothing exceeds the preset threshold, the requirement is met and qualified protective clothing is obtained. If the estimated value of the quality of the protective clothing is less than the preset threshold, the requirement is not met and the protective clothing is discarded as unqualified.

[0086] Example 2: Based on the processing quality evaluation method applied to protective clothing production in Example 1, the present invention is further illustrated and described below.

[0087] like Figure 1 As shown, a processing quality evaluation method applied to protective clothing production comprises:

[0088] M1. During the processing of protective clothing, the image data information of the protective clothing is obtained in real time based on the camera on the production line, and the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing are collected;

[0089] M2. Based on the image data information of the protective clothing, the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing, a processing quality prediction model of the protective clothing is constructed to predict the processing quality of the protective clothing, and obtain data information of the predicted processing quality of the protective clothing;

[0090] M3. Based on the predicted data information of the processing quality of the protective clothing, a processing quality parameter optimization model of the protective clothing is constructed, and the processing quality parameters of the protective clothing are optimized to obtain the parameter data information of the processing quality of the optimized protective clothing;

[0091] M4. Based on the parameter data information of the processing quality of the optimized protective clothing, the quality of the protective clothing is estimated using an improved maximum relevance minimum redundancy algorithm to obtain estimated value data information of the quality of the protective clothing.

[0092] In this embodiment, if Figure 3 As shown, in step M3, a processing quality parameter optimization model of protective clothing is constructed, and the processing quality parameters of protective clothing are optimized including:

[0093] M31. Based on the data information of the processing quality of the protective clothing after the prediction, a Gaussian kernel function R of the protective clothing is established.

[0094]

[0095] Among them, a is the data information of the processing quality of the protective clothing after prediction, γ1, γ2 and γ3 are weight coefficients, and the state parameter matrix of the protective clothing is characterized to obtain the state parameter matrix data information of the protective clothing;

[0096] M32. Based on the state parameter matrix data information of the protective clothing, an optimization function U of the processing quality parameters of the protective clothing is established.

[0097]

[0098] Among them, b is the state parameter matrix data information of the protective clothing, η1 and η2 are the hyperparameters of the model;

[0099] M33. Based on the optimization function U of the processing quality parameters of the protective clothing, the processing quality parameters of the protective clothing are optimized to obtain parameter data information of the processing quality of the optimized protective clothing.

[0100] In this embodiment, in step M32, the hyperparameters η1 and η2 of the model are,

[0101] Among them, b is the state parameter matrix data information of the protective clothing.

[0102] In this embodiment, in step M4, the use of the improved maximum relevance minimum redundancy algorithm to estimate the quality of the protective clothing includes:

[0103] M41. Based on the parameter data information of the processing quality of the optimized protective clothing, establish the mutual information value function G of the protective clothing,

[0104]

[0105] Among them, c is the parameter data information of the processing quality of the protective clothing after optimization, λ1 and λ2 are the correlation factors of the protective clothing, and the mutual information value of the protective clothing is calculated to obtain the mutual information value data information of the protective clothing;

[0106] M42. Based on the mutual information value data information of the protective clothing, establish a quality estimation function H of the protective clothing,

[0107]

[0108] Among them, r is the mutual information value data information of the protective clothing, ρ1, ρ2 and ρ3 are the quality determining factors of the protective clothing;

[0109] M43. Based on the quality estimation function H of the protective clothing, the quality of the protective clothing is estimated to obtain estimated value data information of the quality of the protective clothing.

[0110] In this embodiment, in step M42, the quality determining factors ρ1, ρ2 and ρ3 of the rice husk are:

[0111]

[0112] Among them, r is the mutual information value data information of the protective clothing.

[0113] In this embodiment, the present invention provides a processing quality evaluation system applied to protective clothing production, including a computer device, which is programmed or configured to execute any one of the steps of the processing quality evaluation method applied to protective clothing production.

[0114] The present invention also provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the processing quality evaluation methods for protective clothing production.

[0115] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0116] In summary, the present invention can not only accurately detect the protective clothing, but also the detection process does not require human intervention, thereby reducing labor costs and improving the production efficiency of protective clothing.

[0117] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A processing quality evaluation method applied to protective clothing production, characterized in that: The method comprises: M1. During the processing of protective clothing, the image data information of the protective clothing is obtained in real time based on the camera on the production line, and the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing are collected; M2. Based on the image data information of the protective clothing, the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing, a processing quality prediction model of the protective clothing is constructed to predict the processing quality of the protective clothing, and obtain data information of the predicted processing quality of the protective clothing; M3. Based on the predicted data information of the processing quality of the protective clothing, a processing quality parameter optimization model of the protective clothing is constructed, and the processing quality parameters of the protective clothing are optimized to obtain the parameter data information of the processing quality of the optimized protective clothing; M4. Based on the parameter data information of the processing quality of the optimized protective clothing, the quality of the protective clothing is estimated using an improved maximum relevance minimum redundancy algorithm to obtain estimated value data information of the quality of the protective clothing.

2. The processing quality evaluation method for protective clothing production according to claim 1 is characterized in that: In step M2, the step of constructing a processing quality prediction model for protective clothing and predicting the processing quality of protective clothing includes: M21. Based on the image data information of the protective clothing, the data information of the cutting size of the protective clothing and the data information of the sewing process parameters of the protective clothing, construct a feature extraction function F of the protective clothing, Among them, x1 is the image data information of the protective clothing, x2 is the data information of the cutting size of the protective clothing, x3 is the data information of the sewing process parameters of the protective clothing, α1, α2 and α3 are the feature extraction constant parameters of the protective clothing, and the relevant parameters of the protective clothing are feature extracted to obtain the feature matrix data information of the relevant parameters of the protective clothing; M22. Based on the characteristic matrix data information of the relevant parameters of the protective clothing, a contribution function Q of the relevant parameters of the protective clothing is established. Among them, y is the characteristic matrix data information of the relevant parameters of the protective clothing, β1, β2 and β3 are the error penalty coefficients of the protective clothing, and the contribution values ​​of the relevant parameters of the protective clothing are calculated to obtain the contribution value data information of the relevant parameters of the protective clothing; M23. Based on the contribution value data information of the relevant parameters of the protective clothing, a processing quality prediction function W of the protective clothing is established. Among them, z is the contribution value data information of the relevant parameters of the protective clothing, δ1, δ2 and δ3 are the bias constant parameters of the model, and the processing quality of the protective clothing is predicted to obtain the data information of the predicted processing quality of the protective clothing.

3. The processing quality evaluation method for protective clothing production according to claim 2 is characterized in that: In step M23, the bias constant parameters δ1, δ2 and δ3 of the model are, Among them, z is the contribution value data information of the relevant parameters of the protective clothing.

4. The processing quality evaluation method for protective clothing production according to claim 2 is characterized in that: In step M22, the constraints of the error penalty coefficients β1, β2 and β3 of the protective clothing are:

5. The processing quality evaluation method for protective clothing production according to claim 2 is characterized in that: In step M21, the constraint function f of the feature extraction constant parameters α1, α2 and α3 of the protective clothing is, The value range of f is (0,1).

6. The processing quality evaluation method for protective clothing production according to claim 1 is characterized in that: The method further comprises: M5. Based on the estimated value data information of the quality of the protective clothing, a preset threshold is set. If the estimated value of the quality of the protective clothing exceeds the preset threshold, the requirement is met and qualified protective clothing is obtained. If the estimated value of the quality of the protective clothing is less than the preset threshold, the requirement is not met and the protective clothing is discarded as unqualified.

7. The processing quality evaluation method for protective clothing production according to claim 1 is characterized in that: In step M3, a processing quality parameter optimization model of the protective clothing is constructed, and the processing quality parameters of the protective clothing are optimized including: M31. Based on the data information of the processing quality of the protective clothing after the prediction, a Gaussian kernel function R of the protective clothing is established. Among them, a is the data information of the processing quality of the protective clothing after prediction, γ1, γ2 and γ3 are weight coefficients, and the state parameter matrix of the protective clothing is characterized to obtain the state parameter matrix data information of the protective clothing; M32. Based on the state parameter matrix data information of the protective clothing, an optimization function U of the processing quality parameters of the protective clothing is established. Among them, b is the state parameter matrix data information of the protective clothing, η1 and η2 are the hyperparameters of the model; M33. Based on the optimization function U of the processing quality parameters of the protective clothing, the processing quality parameters of the protective clothing are optimized to obtain parameter data information of the processing quality of the optimized protective clothing.

8. The processing quality evaluation method for protective clothing production according to claim 7 is characterized in that: In step M32, the hyperparameters η1 and η2 of the model are, Among them, b is the state parameter matrix data information of the protective clothing.

9. The processing quality evaluation method for protective clothing production according to claim 1 is characterized in that: In step M4, the use of the improved maximum relevance minimum redundancy algorithm to estimate the quality of the protective clothing includes: M41. Based on the parameter data information of the processing quality of the optimized protective clothing, establish the mutual information value function G of the protective clothing, Among them, c is the parameter data information of the processing quality of the protective clothing after optimization, λ1 and λ2 are the correlation factors of the protective clothing, and the mutual information value of the protective clothing is calculated to obtain the mutual information value data information of the protective clothing; M42. Based on the mutual information value data information of the protective clothing, establish a quality estimation function H of the protective clothing, Among them, r is the mutual information value data information of the protective clothing, ρ1, ρ2 and ρ3 are the quality determining factors of the protective clothing; M43. Based on the quality estimation function H of the protective clothing, the quality of the protective clothing is estimated to obtain estimated value data information of the quality of the protective clothing.

10. The processing quality evaluation method for protective clothing production according to claim 9 is characterized in that: In step M42, the quality determining factors ρ1, ρ2 and ρ3 of the rice husk are, Among them, r is the mutual information value data information of the protective clothing.

Images