System and method for proportioning adhesive lining rubber powder for policeman uniform

Abstract

The invention discloses an adhesive lining rubber powder proportioning system and method for a police uniform, and relates to the technical field of rubber powder proportioning. Comprising the steps of obtaining a matching core parameter group based on production demand data of the police uniform, pre-obtaining the production demand data which at least comprises a police uniform fabric type, an adhesive strength standard, a washable coefficient requirement, an environmental protection index limit value and a use environment working condition, generating a multi-target matching scheme based on the matching core parameter group, the proportioning scheme at least comprises any one or combination of more of a basic proportioning scheme, a performance optimization proportioning scheme and a cost control proportioning scheme. Core parameter sets such as the police uniform fabric type, the bonding strength and the washable coefficient are extracted through the demand analysis module, the proportion of matrix resin, a curing agent, filler and a functional additive is optimized in combination with an intelligent proportion model, a customized scheme is generated according to different fabric characteristics, and the problem that a traditional general formula is poor in adaptability is effectively solved.

Description

TECHNICAL FIELD

[0001] The application relates to a rubber powder proportioning system and method for adhesive lining of police uniforms. BACKGROUND

[0002] The rubber powder formula of the adhesive lining for police uniforms directly determines the adhesive strength, wash resistance, wearing comfort and service life of the police uniforms, and needs to meet the requirements of the GA740-2007 police uniform standard and the environmental protection VOC content limit value. With the diversified development of police uniform fabrics and the improvement of the performance requirements such as wear resistance, wrinkle resistance and wash resistance of police uniforms in the working environment, the rubber powder proportioning needs to achieve the multi-objective balance of fabric adaptation, performance standard, environmental protection compliance and cost control.

[0003] However, the existing proportioning lacks specificity, and a general formula is often used to adapt to different police uniform fabrics, which is prone to loose adhesion and insufficient wash resistance, and it is difficult to meet the individualized needs of specific fabrics and working scenes, and the multi-objective balance ability is weak. Traditional proportioning focuses on single performance optimization and ignores the coordinated control of environmental protection indicators and production costs, resulting in substandard environmental protection or high cost. The existing proportioning precision and efficiency are low, and the proportioning result stability is poor.

[0004] Therefore, the application provides a rubber powder proportioning system and method for adhesive lining of police uniforms. SUMMARY

[0005] The application aims to provide a rubber powder proportioning system and method for adhesive lining of police uniforms to solve the problems in the background art.

[0006] To achieve the above-mentioned purpose, the application provides the following technical solution: a rubber powder proportioning method for adhesive lining of police uniforms, which is applied to precise deployment of rubber powder for hot melt adhesive lining of police uniforms, and the rubber powder for adhesive lining of police uniforms at least includes any three or more combinations of base resin, curing agent, filler and functional additive, and comprises:

[0007] Based on the production demand data of police uniforms, a proportioning core parameter group is obtained, and the production demand data is obtained in advance and at least includes the type of police uniform fabric, the standard of adhesive strength, the requirement of wash resistance coefficient, the limit value of environmental protection index and the working condition of use environment;

[0008] Based on the proportioning core parameter group, a multi-objective proportioning scheme is generated, and the proportioning scheme at least includes any one or more combinations of a basic proportioning scheme, a performance optimization proportioning scheme and a cost control proportioning scheme;

[0009] iterating parameters in an intelligent proportioning model based on the proportioning scheme, to obtain a plurality of first proportioning results; the intelligent proportioning model is pre-established based on a historical proportioning database and a multi-objective optimization algorithm; the historical proportioning database is pre-constructed based on historical formula data, performance detection data and raw material characteristic data of adhesive lining rubber powder for police uniforms;

[0010] obtaining a first adaptation value corresponding to each first proportioning result; the first adaptation value is used at least to represent a matching degree of the corresponding first proportioning result and a core parameter of production demand data, including an adhesive strength adaptation score, a washing resistance performance adaptation score, an environmental protection compliance adaptation score and a cost adaptation score;

[0011] obtaining a plurality of second proportioning results based on each first adaptation value; the second proportioning result is any first proportioning result meeting a first preset condition, and the first preset condition is that a first adaptation value comprehensive score is not less than a preset threshold;

[0012] generating a final proportioning scheme based on each second proportioning result and combining production process parameters, the production process parameters at least including hot pressing temperature, shearing time and stirring rate.

[0013] As a specific scheme of the technical scheme of the present application, the intelligent proportioning model includes a raw material characteristic extraction network, a parameter mapping network and a multi-objective loss function network;

[0014] The intelligent proportioning model is pre-established based on the historical proportioning database by the following way:

[0015] obtaining a multi-dimensional feature code based on raw material data in the historical proportioning database based on the raw material feature extraction network; the multi-dimensional feature code at least includes base resin viscosity characteristics, curing agent reactivity characteristics, filler particle size distribution characteristics and additive functional property characteristics;

[0016] obtaining a proportioning parameter vector set based on the multi-dimensional feature code based on the parameter mapping network; the proportioning parameter vector set includes a weight proportion vector, a performance prediction vector and a cost vector of each raw material;

[0017] obtaining a final loss value based on the proportioning parameter vector set based on the multi-objective loss function network;

[0018] if the final loss value meets a second preset condition, obtaining the intelligent proportioning model based on the current raw material characteristic extraction network, parameter mapping network and multi-objective loss function; otherwise, updating weight parameters of the raw material characteristic extraction network and the parameter mapping network, re-obtaining the final loss value, until the final loss value meets the second preset condition.

[0019] As a specific scheme of the technical scheme of the present application, the matching parameter vector set includes a first parameter vector group and a second parameter vector group; the first parameter vector group is a positive sample matching vector and a negative sample matching vector corresponding to different police uniform fabric types; the second parameter vector group is an optimal matching vector set under the same performance level requirement; the final loss value is obtained based on the multi-objective loss function network and the matching parameter vector set, including:

[0020] The performance loss value is obtained based on the first parameter vector group; the performance loss value represents the deviation of the matching scheme from the police uniform fabric type;

[0021] The compliance loss value is obtained based on the second parameter vector group; the compliance loss value represents the deviation of the matching scheme from the GA740-2007 standard and the VOC content limit standard;

[0022] The final loss value is obtained based on the performance loss value and the compliance loss value.

[0023] As a specific scheme of the technical scheme of the present application, the final loss value is obtained based on the performance loss value and the compliance loss value, including:

[0024] The first performance matrix and the second performance matrix are obtained based on the first parameter vector group, the first performance matrix being a performance detection result matrix of the positive sample matching vector, and the second performance matrix being a performance detection result matrix of the negative sample matching vector;

[0025] The first deviation sum is obtained based on the first performance matrix; the first deviation sum is used at least to represent the difference between the positive sample matching scheme and the optimal performance index;

[0026] The second deviation sum is obtained based on the second performance matrix; the second deviation sum is used at least to represent the difference between the negative sample matching scheme and the qualified performance index;

[0027] The process adaptation loss value is obtained based on the first deviation sum and the second deviation sum;

[0028] The final loss value is obtained by weighted summation based on the performance loss value, the compliance loss value and the process adaptation loss value.

[0029] As a specific scheme of the technical scheme of the present application, the basic matching scheme includes:

[0030] Based on the basic performance requirements in the core parameter group, the highest matching reference formula in the historical matching database is called, and the basic matching result is obtained by proportionally adjusting the material characteristics parameters, wherein the basic performance requirements at least include a peeling strength ≥ 3.5 N / 25 mm and a washing resistance coefficient ≥ 50 times;

[0031] The performance optimization matching scheme includes:

[0032] Based on the high performance requirements in the core parameter group, the matching proportion of the matrix resin and the curing agent is optimized by the response surface method, the particle size distribution of the filler and the addition amount of the functional additive are adjusted, and the performance optimization matching result is obtained, wherein the high performance requirements at least include a peeling strength ≥ 5.0 N / 25 mm, a washing resistance times ≥ 100 times, and a performance retention rate after heat aging ≥ 90%;

[0033] The cost control matching scheme includes:

[0034] Based on the cost budget requirements of the core parameter group, the proportion of the filler and the matrix resin is optimized under the premise of meeting the basic performance standards, and a high cost-effective functional additive replacement scheme is selected to obtain the cost control matching result, wherein the cost budget requirement is that the cost of the unit weight of the rubber powder is not more than a preset threshold.

[0035] As a specific scheme of the technical scheme of the present application, the multi-target matching scheme is generated based on the core parameter group, including:

[0036] Based on the core parameter group, at least one second adaptation value is obtained, and the second adaptation value is the matching degree of the existing formula in the historical matching database and the core parameter group;

[0037] If there is an existing formula with a second adaptation value ≥ an adaptation threshold, a basic matching scheme is generated first, otherwise, a combination of the basic matching scheme and the performance optimization matching scheme is generated, and if there is a cost constraint, a cost control matching scheme is added.

[0038] As a specific scheme of the technical scheme of the present application, the first adaptation value corresponding to each first matching result is obtained, including:

[0039] Based on each first matching result, a third matching result is obtained; the third matching result is a current matching scheme in each first matching result for sequentially calculating the adaptation value;

[0040] Based on the third matching result, each dimension adaptation sum and weight coefficient are obtained; the weight coefficient is based on the priority setting in the production demand data, wherein the performance adaptation sum weight ≥ 0.5 in a high performance demand scenario, the environmental protection compliance adaptation sum weight ≥ 0.4 in an environmental protection strict control scenario, and the cost adaptation sum weight ≥ 0.4 in a cost sensitive scenario;

[0041] A third matching result corresponding to the first matching value is obtained by weighted summation based on the dimension adaptation score and the weight coefficient.

[0042] As a specific solution of the technical solution of the present application, after the final matching scheme is generated, the method further comprises:

[0043] Actual production detection data corresponding to the final matching scheme is obtained; the actual production detection data at least includes peeling strength detection value, performance retention rate after washing, VOC content detection value and production qualification rate;

[0044] Based on the actual production detection data, an optimization adjustment coefficient corresponding to the final matching scheme is obtained; the optimization adjustment coefficient is used to correct the parameter mapping network of the intelligent matching model;

[0045] Based on the optimization adjustment coefficient, the intelligent matching model historical matching database is updated, and the updating includes supplementing actual detection data, adjusting weight parameters and optimizing loss function coefficients.

[0046] A police uniform adhesive lining powder matching system is applied to precise deployment of hot melt adhesive lining powder for police uniforms, and the adhesive lining powder for police uniforms at least includes any three or more combinations of base resin, curing agent, filler and functional additive, comprising:

[0047] A demand analysis module is used to obtain matching core parameter groups based on police uniform production demand data; the production demand data is pre-obtained and at least includes police uniform fabric type, adhesive strength standard, washing frequency requirement, environmental protection index limit value and use environment working condition;

[0048] A scheme generation module is used to generate multi-objective matching schemes based on the matching core parameter groups; the matching schemes at least include any one or more combinations of basic matching schemes, performance optimization matching schemes and cost control matching schemes;

[0049] An iterative calculation module is used to perform parameter iteration in an intelligent matching model based on the matching schemes to obtain a plurality of first matching results; the intelligent matching model is pre-established based on a historical matching database and a multi-objective optimization algorithm; the historical matching database is pre-constructed based on historical formula data, performance detection data and raw material characteristic data of the adhesive lining powder for police uniforms;

[0050] An adaptation evaluation module is used to obtain first matching values corresponding to each first matching result; the first matching values at least are used to represent the matching degree of the corresponding first matching result and the core parameters in the production demand data, including adhesive strength adaptation score, washing performance adaptation score, environmental protection compliance adaptation score and cost adaptation score;

[0051] A scheme screening module is configured to obtain a plurality of second matching results based on the respective first matching values; the second matching result is any first matching result meeting a first preset condition, and the first preset condition is that the first matching value comprehensive score is not lower than a preset threshold;

[0052] A final output module is configured to generate a final matching scheme based on the respective second matching results and in combination with production process parameters; the production process parameters at least include hot-pressing temperature, shearing time and stirring speed.

[0053] A computer readable storage medium has a computer program stored thereon, and the computer program is executed by a processor to implement the adhesive lining rubber powder matching method for police uniforms according to any one of the embodiments.

[0054] Compared with the prior art, the adhesive lining rubber powder matching method for police uniforms has the following beneficial effects:

[0055] The demand analysis module extracts core parameter groups such as police uniform fabric types, adhesive strength and wash resistance coefficients, and an intelligent matching model is combined to optimize the matching of base resins, curing agents, fillers and functional additives, customized schemes are generated for different fabric characteristics, and the poor adaptability of traditional general formulations is effectively solved.

[0056] Meanwhile, the intelligent matching model is constructed based on a historical matching database, multi-dimensional features such as resin viscosity and curing agent reactivity are extracted through a raw material characteristic extraction network, and rapid iterative calculation is realized through parameter mapping network and multi-objective optimization algorithm, so that the matching cycle is shortened and the production consistency is improved.

[0057] After the final matching scheme is generated, detection data such as peel strength, wash retention rate and VOC content in actual production are collected to obtain an optimization adjustment coefficient, the intelligent matching model and the historical database are continuously updated, and the matching scheme after model correction can ensure performance standards, and the problem that traditional matching cannot cope with production fluctuations is solved. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 A flowchart of the adhesive lining rubber powder matching method for police uniforms according to the embodiments of the present application is shown in the figure.

[0059] Figure 2 A structure diagram of the adhesive lining rubber powder matching system for police uniforms according to the embodiments of the present application is shown in the figure. DETAILED DESCRIPTION

[0060] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work belong to the scope of protection of the present application.

[0061] To solve the technical problems that the existing adhesive powder ratio method for police uniforms cannot balance performance standard, environmental protection compliance and cost optimization, and the ratio precision is insufficient, and it is difficult to adapt to different police uniform fabrics and use scenarios as proposed in the background art, an embodiment of a police uniform adhesive powder ratio system and method is proposed. As shown in Figure 1 The police uniform adhesive powder ratio method includes steps S100 to S600.

[0062] Step S100: Obtain police uniform production demand data and extract a core parameter group.

[0063] The core goal of this step is to accurately capture the personalized needs of police uniform production, and to provide clear basis for subsequent ratio scheme generation. The production demand data is obtained in advance, and at least includes police uniform fabric type, adhesive strength standard, washing frequency requirement, environmental protection index limit value and use environment working condition.

[0064] In the embodiments of the present application, the police uniform production demand data can be obtained in any reasonable way. For example, if the police uniform production enterprise has established a standardized production demand management system, the demand information corresponding to the order can be directly read through the system interface, and the data can be extracted according to the classification fields of “fabric type, performance level, environmental protection requirement, cost budget”. For example, in the system “2025 police uniform production order” module, the order data of a batch of on-duty police uniforms is called, and the key information such as fabric type “polyester blend”, adhesive strength standard “peeling strength ≥4.0N / 25mm”, washing frequency requirement ≥80 times, VOC content limit value ≤50g / L and use environment working condition, outdoor wear and tear scene, etc. is directly obtained.

[0065] Alternatively, for small-batch customized police uniform production demand, demand data can be collected through a structured questionnaire. The questionnaire includes core issues such as fabric material, use scenario (such as on-duty, formal wear, training, etc.), performance priority (such as priority for strong adhesion, priority for high washing resistance or priority for low odor), cost control range, etc. After collection, invalid information is removed through data cleaning tools, qualitative description (such as high washing resistance) is converted into quantitative index (such as washing frequency ≥100 times), and finally the core parameter group is integrated to form a ratio.

[0066] In one specific embodiment of the present application, step S100 includes steps S110 to S130.

[0067] Step S100: Collect basic demand information, including the use scenarios of police uniforms (outdoor duty, indoor office, special environment operation, etc.), fabric materials (pure cotton, polyester, polyester fiber, functional composite fabric, etc.), and production batch (large batch production, small batch customization).

[0068] Step S120: Convert quantitative performance indicators, based on the GA740-2007 police uniform standard and industry testing specifications, the basic demand information is converted into quantifiable performance parameters. For example, the outdoor duty police uniform corresponds to a peel strength ≥ 5.0 N / 25 mm, a washing resistance ≥ 100 times, and a performance retention rate ≥ 90% after heat aging. The indoor office police uniform corresponds to a peel strength ≥ 3.5 N / 25 mm, a washing resistance ≥ 50 times, and a VOC content ≤ 75 g / L.

[0069] Step S130: Integrate the core parameter group, integrate the fabric type, quantitative performance indicators, environmental protection limits (such as VOC content, heavy metal residue requirements), and cost budget (such as unit weight of glue powder cost ≤ X yuan), and form a structured matching core parameter group to ensure that each parameter has a clear numerical value or range definition.

[0070] Step S200: Based on the matching core parameter group, generate a multi-objective matching scheme

[0071] This step aims to construct a matching scheme set covering different scenarios according to the demand priority, which includes at least any one or more combinations of the basic matching scheme, the performance optimization matching scheme, and the cost control matching scheme.

[0072] It should be noted that the police uniform as a special functional clothing, the matching of its adhesive lining needs to meet multiple constraints at the same time. It needs to ensure the core performance such as adhesion strength and washing resistance to adapt to the high-intensity use demand of police work, meet the environmental protection standards to protect the health of the wearer, and control the cost to adapt to different production budgets. The existing matching method mostly uses a single fixed formula or simply adjusts the proportion of raw materials, which cannot meet the multi-objective balance demand, resulting in either performance surplus causing cost waste or cost being too low leading to substandard performance or exceeding environmental protection standards. Therefore, this step realizes precise adaptation in different demand scenarios through multi-scheme design.

[0073] In one specific embodiment of the present application, step S200 includes steps S210 to S230.

[0074] Step S210: Calculate the second adaptive value, match the historical formula

[0075] Based on the core parameter group, at least one second adaptation value is obtained, which is the matching degree of the existing formula in the historical matching database and the core parameter group. In the matching calculation, the weighted scoring method is adopted, and each parameter is given a weight according to the demand priority, for example, in the high-performance demand scenario, the fabric adaptation weight is 0.3, the adhesion strength weight is 0.3, the wash resistance weight is 0.2, the environmental protection weight is 0.1, and the cost weight is 0.1. In the cost-sensitive scenario, the cost weight is 0.4, the basic performance weight is 0.3, the environmental protection weight is 0.2, and the fabric adaptability weight is 0.1.

[0076] Step S220: Generating a basic matching scheme

[0077] If there is an existing formula with a second adaptation value ≥ adaptation threshold (such as an adaptation threshold of 0.85), a basic matching scheme is generated first. This scheme is based on the historical optimal matching formula, and the raw material characteristic parameters are fine-tuned. The highest matching degree of the reference formula in the historical matching database is retrieved, and the characteristic differences of the current raw material batch (such as basic numerical viscosity fluctuation and filler particle size deviation) are combined to fine-tune the proportion of each raw material within ±5%, ensuring that the basic performance requirements are met (at least including peel strength ≥ 3.5N / 25mm, and wash resistance ≥ 50 times). For example, if the current resin viscosity is 10% higher than the historical average, the proportion of the base resin is adjusted to 43%, and the proportion of the curing agent is fine-tuned from 8% to 8.5% to ensure sufficient adhesion reaction.

[0078] Step S230: Generating an optimized matching scheme

[0079] If there is no existing formula with a second adaptation value ≥ adaptation threshold, a combination of the basic matching scheme and the performance optimization matching scheme is generated; if there is a cost constraint (such as the cost of unit weight of rubber powder not exceeding a preset threshold), a cost control matching scheme is added.

[0080] Performance optimization matching scheme: For high-performance requirements in the core parameter group, the proportion of base resin and curing agent is optimized by response surface method, the particle size distribution of fillers (20-100 mesh range) and the amount of functional additives (0.5%-3% range optimization) are adjusted to obtain performance optimization matching results. For example, for the demand of peel strength ≥ 5.0N / 25mm and wash resistance ≥ 100 times, the proportion of base resin and curing agent is optimized from 5:1 to 4:1, 80-100 mesh fillers are selected to improve adhesion stability, and 1.5% anti-aging additives are added to enhance wash resistance.

[0081] Cost control matching scheme, under the premise of meeting the basic performance standards, optimize the ratio of filler and matrix resin, select high cost-effective additives instead of scheme. For example, under the basic requirement of stripping strength ≥ 3.5N / 25mm, increase the proportion of filler from 30% to 35%, while select industrial grade high purity filler instead of special filler, select domestic substitute products for functional machine, reduce unit cost under the premise of not affecting performance.

[0082] Step S300: obtaining a first matching result based on intelligent matching model iterative calculation

[0083] This step iteratively optimizes the parameters of the multi-objective matching scheme through the preselected intelligent matching model, and outputs multiple first matching results that meet the basic constraints. The intelligent matching model is pre-established based on a historical matching database and a multi-objective optimization algorithm. The historical matching database is pre-constructed based on historical formula data, performance detection data, and raw material characteristic data of adhesive lining rubber powder for police uniforms.

[0084] It should be noted that fluctuations in raw material characteristics (such as changes in matrix resin viscosity, differences in curing agent reactivity) and slight fluctuations in production processes will cause deviations in the final performance of the same formula. Existing models often ignore the dynamic impact of raw material characteristics and only calculate based on fixed parameters, resulting in insufficient actual adaptability of the matching results. The intelligent matching model of the present application achieves precise matching of formula parameters, raw material characteristics, and demand indicators by extracting multi-dimensional features of raw materials and combining multi-objective loss function optimization.

[0085] In one specific embodiment of the present application, step S300 includes steps S310 to S340:

[0086] Step S310: constructing an intelligent matching model

[0087] The intelligent matching model includes a raw material characteristic extraction network, a parameter mapping network, and a multi-objective loss function network, and its establishment process is as follows:

[0088] Based on the raw material characteristic extraction network, multi-dimensional feature codes are obtained from the raw material data in the historical matching database, including at least matrix resin viscosity characteristics, curing agent reactivity characteristics, filler particle size distribution characteristics, and additive functional property characteristics. For example, the temperature response curve characteristics of resin viscosity, the particle size distribution histogram characteristics of filler, and the conversion to 128-dimensional feature vectors are extracted through a convolutional neural network.

[0089] Based on the parameter mapping network, the multi-dimensional feature code is mapped into a set of matching parameter vectors, including weight proportion vectors of each raw material, performance prediction vectors and cost vectors. The parameter mapping network adopts a fully connected layer structure, and realizes nonlinear mapping of features to parameters through an activation function, ensuring that the output matching parameters are within a reasonable range (such as 30%-50% for the base resin and 5%-10% for the curing agent).

[0090] Based on the multi-objective loss function network, the final loss value is obtained from the set of matching parameter vectors. If the final loss value meets the second preset condition (such as loss value ≤ 0.05), the current model is determined as the final intelligent matching model, otherwise, the weight parameters of the raw material characteristic extraction network and the parameter mapping network are updated, and the loss value is recalculated until the preset condition is met.

[0091] Step S320: Decompose the matching parameter vector set

[0092] The matching parameter vector set includes a first parameter vector group and a second parameter vector group. The first parameter vector group is a positive sample matching vector (a formula that meets performance standards) and a negative sample matching vector (a formula that does not meet performance standards) corresponding to different police uniform fabric types. The second parameter vector group is a set of optimal matching vectors under the same performance level requirement.

[0093] Step S330: Calculate multi-dimensional loss value

[0094] Based on the first parameter vector group, the performance loss value is obtained, which represents the deviation of the matching scheme from the police uniform fabric type. The loss function is calculated based on the performance difference between the positive sample and the negative sample.

[0095] Based on the second parameter vector group, the compliance loss value is obtained, which represents the deviation of the matching scheme from the GA740-2007 standard and the VOC content limit standard. The difference between the formula parameters and the standard threshold is calculated.

[0096] Based on the positive sample performance matrix and the negative sample performance matrix in the first parameter vector group, the first deviation sum (the difference between the positive sample and the optimal performance indicator) and the second deviation sum (the difference between the negative sample and the qualified performance indicator) are obtained, and then the process adaptation loss value (representing the matching degree of the formula with the production process) is calculated.

[0097] Based on the performance loss value, the compliance loss value and the process adaptation loss value, the final loss value is obtained by weighted summation, and the weights are set according to the demand priority (such as performance loss value weight 0.4, compliance loss value weight 0.3, process adaptation loss value weight 0.3 in the performance limited scenario).

[0098] Step S340: Parameter iteration to obtain the first matching result

[0099] Input the multi-target matching scheme generated in step S200 into the intelligent matching model, and perform parameter iteration optimization with the goal of minimizing the final loss value. Each iteration adjusts the parameter values of the raw material proportion vector, performance prediction vector, and cost vector. The number of iterations is set to 50-200 times (which can be adjusted according to the required accuracy), and after the iteration is completed, multiple first matching results that satisfy the loss value ≤ preset threshold are output.

[0100] Step S400: Calculate the first adaptation value and filter the second matching result

[0101] This step selects the scheme that highly matches the demand from the first matching result through multi-dimensional adaptation evaluation. The first adaptation value is used to represent at least the matching degree of the corresponding first matching result with the core parameters of the production demand data, including the bonding strength adaptation score, the washing resistance adaptation score, the environmental protection compliance adaptation score, and the cost adaptation score. The second matching result is any first matching result that meets the first preset condition (the comprehensive score of the first adaptation value is not less than the preset threshold, such as 85 points).

[0102] In one specific embodiment of the present application, step S400 includes steps S410 to S430:

[0103] Step S410: Select the third matching result one by one, i.e., calculate the adaptation value for each first matching result in order.

[0104] Step S420: Calculate the dimension adaptation score and weight coefficient. The dimension adaptation score is quantitatively calculated according to the detection standard (such as ; ), and the weight coefficient is set based on the priority in the production demand data, wherein the performance adaptation score weight ≥ 0.5 in the high-performance demand scenario, the environmental protection compliance adaptation score weight ≥ 0.4 in the strict environmental protection scenario, and the cost adaptation score weight ≥ 0.4 in the cost-sensitive scenario.

[0105] Step S430: Calculate the first adaptation value by weighted summation, the formula is:

[0106] Filter the first matching result with a comprehensive score ≥ 85 points as the second matching result.

[0107] Step S500: Generate the final matching scheme combined with the production process parameters

[0108] This step combines the filtered second matching result with the actual production process conditions to form the final matching scheme. The production process parameters include at least hot pressing temperature (120-160℃), shearing time (30-120s), and stirring rate (500-1500r / min).

[0109] It should be noted that the glue powder ratio scheme has a strong correlation with the production process parameters. The same ratio has significant differences in the final bonding effect under different hot pressing temperatures or stirring rates. For example, a high proportion of curing agent ratio needs to be matched with a higher hot pressing temperature to ensure sufficient reaction, and the formula of fine particle filler needs to appropriately increase the stirring rate to avoid agglomeration. Therefore, this step optimizes the process parameters and the ratio scheme to ensure stable performance of the final product.

[0110] In this embodiment, the specific process of combining production process parameters is as follows: based on the characteristics of each raw material in the second ratio result (such as curing agent reaction temperature, filler dispersity), query the process parameter matching database to obtain the corresponding reference process parameters, and then according to the actual performance of the production equipment (such as the temperature accuracy of the hot press and the power of the stirrer), fine-tune the reference process parameters within ±10%, and finally form a complete final ratio scheme of raw material ratio + process parameters. For example, in a certain second ratio result, the curing agent accounts for ±10%, and the filler particle size is 60 mesh. The corresponding reference process parameters are hot pressing temperature 150°C, shear time 60s, and stirring rate 1200r / min. If the production equipment hot press temperature deviation is ±5°C, the hot pressing temperature is adjusted to 155°C to ensure sufficient curing reaction.

[0111] Step S600: Update the model and database based on actual production detection data

[0112] This step continuously optimizes the intelligent ratio model and historical database through a closed-loop feedback mechanism to improve the accuracy of subsequent ratio.

[0113] In one specific embodiment of the present application, step S600 includes steps S610 to S630:

[0114] Step S610: Obtain actual production detection data, which at least includes peel strength detection value detected according to FZ / T01085-2018 standard, performance retention rate after washing, VOC content detection value detected according to GB33372-2020 standard, and production qualified rate.

[0115] Step S620: Calculate the optimization adjustment coefficient. Based on the deviation between the actual detection data and the predicted value, obtain the limited adjustment coefficient through the proportional coefficient method, for example: The coefficient is used to correct the parameter mapping network of the intelligent ratio model.

[0116] Step S630: Update the model and database. The actual production detection data, the final ratio scheme, and the optimization adjustment coefficient are supplemented to the historical ratio database. The weight parameters of the parameter mapping network in the intelligent ratio model are adjusted based on the optimization adjustment coefficient, and the coefficients of the multi-objective loss function are optimized to ensure continuous improvement of the model prediction accuracy.

[0117] The adhesive lining powder ratio system and method for police uniforms provided in the application realizes the dynamic balance of the three targets of performance, environmental protection and cost through accurate demand parameter extraction, multi-target scheme design, intelligent model iterative optimization, process collaborative adaptation and closed-loop updating mechanism, solves the problems of insufficient accuracy and poor adaptability of traditional ratio schemes, ensures that the adhesive lining powder ratio meets the requirements of police uniform standards and adapts to different production scenarios and budget requirements, and improves the production quality and efficiency of the adhesive lining for police uniforms.

[0118] After introducing the adhesive powder ratio method for police uniforms provided in the embodiment of the application, an embodiment of an adhesive powder ratio system for police uniforms provided in the application will be introduced below. The adhesive powder ratio system for police uniforms is applied to the accurate deployment of adhesive powder for hot melt adhesive lining for police uniforms. The adhesive powder for the adhesive lining for police uniforms at least includes any three or more combinations of base resin, curing agent, filler and functional additive, as shown in Figure 2 The adhesive powder ratio system 20 for police uniforms includes:

[0119] The demand analysis module 21 is used to obtain a ratio core parameter group based on police uniform production demand data. The production demand data is pre-obtained and at least includes police uniform fabric type, adhesive strength standard, washing frequency requirement, environmental protection index limit value and use working condition.

[0120] The scheme generation module 22 is used to generate a multi-target ratio scheme based on the ratio core parameter group. The ratio scheme at least includes any one or more combinations of a basic ratio scheme, a performance optimization ratio scheme and a cost control ratio scheme.

[0121] The iterative calculation module 23 is used to perform parameter iteration in an intelligent ratio model based on the ratio scheme to obtain a plurality of first ratio results. The intelligent ratio model is pre-established based on a historical ratio database and a multi-target optimization algorithm. The historical ratio database is pre-constructed based on historical formula data, performance detection data and raw material characteristic data of adhesive lining powder for police uniforms.

[0122] The adaptation evaluation module 24 is used to obtain a first adaptation value corresponding to each first ratio result. The first adaptation value at least represents the matching degree of the corresponding first ratio result and the core parameters in the production demand data, including adhesive strength adaptation points, washing performance adaptation points, environmental protection compliance adaptation points and cost adaptation points.

[0123] The scheme screening module 25 is used to obtain a plurality of second ratio results based on each first adaptation value. The second ratio result is any first ratio result that meets the first preset condition. The first preset condition is that the comprehensive score of the first adaptation value is not less than a preset threshold.

[0124] The final output module 26 is configured to generate a final matching scheme based on the respective second matching result and in combination with production process parameters, wherein the production process parameters at least include hot-pressing temperature, shearing time and stirring speed.

[0125] As a specific solution in the technical scheme, the demand analysis module 21 is further configured to obtain fabric characteristic parameters based on the type of the police uniform fabric, wherein the fabric characteristic parameters at least include fabric fiber composition, fabric density and surface roughness.

[0126] Further, the performance threshold parameters are obtained based on the bonding strength standard and the washing frequency requirement, wherein the performance threshold parameters are the minimum bonding strength value and the minimum washing cycle frequency that meet the use requirement.

[0127] Further, the harmful substance control parameters are obtained based on the environmental protection index limit, wherein the harmful substance parameters at least include a formaldehyde content limit, a heavy metal residue limit and a volatile organic compound emission limit.

[0128] Further, the environment adaptation parameters are obtained based on the use environment condition, wherein the environment adaptation parameters at least include a high-low temperature tolerance range, a humidity adaptation interval and a wear intensity grade.

[0129] Further, the matching core parameter group is integrated based on the fabric characteristic parameters, the performance threshold parameters, the harmful substance control parameters and the environment adaptation parameters.

[0130] As a specific solution in the technical scheme, the scheme generation module 22 is further configured to generate a basic matching scheme based on the performance threshold parameters in the matching core parameter group, wherein the proportion of each raw material in the basic matching scheme meets the minimum bonding strength and washing frequency requirement.

[0131] Further, a performance optimization matching scheme is generated based on the performance threshold parameters and the environment adaptation parameters, wherein the performance optimization matching scheme enhances the bonding stability and the environmental adaptability by improving the purity of the base resin and optimizing the type of the curing agent.

[0132] Further, a cost control matching scheme is generated based on the harmful substance control parameters and raw material market price data, wherein the cost control matching scheme selects high-performance-price ratio fillers and functional additives to replace part of the high-priced raw materials on the premise of meeting the environmental protection requirement.

[0133] Further, the basic matching scheme, the performance optimization matching scheme and the cost control matching scheme are subjected to feasibility verification based on the production batch of the police uniform and the production cycle requirement, and the matching scheme that meets the production condition is reserved as a multi-objective matching scheme.

[0134] As a specific scheme in the technical scheme of the present application, the iteration calculation module 23 is further configured to extract a historical data subset matching the current matching core parameter group from a historical matching database, wherein the historical data subset includes formula data and detection results corresponding to similar fabric types and similar performance requirements;

[0135] In addition, based on the historical data subset, an initial parameter range of an intelligent matching model is determined, wherein the initial parameter range includes weight intervals of each raw material and raw material mixing order parameters;

[0136] In addition, a multi-objective optimization method is used to iteratively optimize parameters within the initial parameter range, and in the iterative optimization process, the maximum adhesion strength, the optimal washing frequency, the minimum cost, and the 100% environmental protection compliance rate are used as objective functions;

[0137] In addition, after each iteration, an intermediate matching result is obtained, and the performance compliance of the intermediate matching result is verified by a simulation detection model, wherein the simulation detection model is generated based on historical performance detection data;

[0138] In addition, when the number of iterations reaches a preset number or the objective function value of the intermediate matching result tends to be stable, the iteration is stopped, and a plurality of first matching results are output.

[0139] As a specific scheme in the technical scheme of the present application, the adaptation evaluation module 24 is further configured to perform adhesion strength simulation testing on each first matching result based on an adhesion strength detection standard, obtain an adhesion strength measured value, compare the adhesion strength measured value with an adhesion strength standard in the performance threshold parameter, and calculate an adhesion strength adaptation score;

[0140] In addition, based on a washing performance test specification, a preset number of washing and dry cleaning processes are simulated, the adhesion retention rate of the first matching result is detected, and a washing performance adaptation score is calculated;

[0141] In addition, based on an environmental protection detection standard, the content of harmful substances in the first matching result is detected, compared with an environmental protection index limit value, and an environmental protection compliance adaptation score is calculated;

[0142] In addition, based on a raw material cost accounting formula, the unit weight raw material cost of the first matching result is calculated, compared with a preset cost budget, and a cost adaptation score is calculated;

[0143] In addition, based on a preset weight coefficient, the adhesion strength adaptation score, the washing performance adaptation score, the environmental protection compliance adaptation score, and the cost adaptation score are weighted and summed to obtain the first adaptation value.

[0144] As a specific scheme in the technical scheme of the present application, the scheme screening module 25 is further configured to obtain a preset threshold, the preset threshold is set based on the core demand priority of the police uniform production, and the environmental protection compliance adaptation score of each single item is not less than the minimum qualified score;

[0145] Furthermore, the first adaptation values of each first matching result are compared with the preset threshold one by one, and the first matching result with a comprehensive score not less than the preset threshold is screened out;

[0146] Based on this, the screened first matching result is repeatedly removed, and the result with a formula parameter difference rate greater than a preset difference threshold is retained as a second matching result;

[0147] Furthermore, the second matching result is sorted based on the high and low of the first adaptation value, and a second matching result sequence is formed.

[0148] As a specific scheme in the technical scheme of the present application, the final output module 26 is further configured to obtain raw material characteristic data corresponding to the second matching result, including the melting point, viscosity and reaction activity of each raw material;

[0149] Furthermore, based on the raw material characteristic data, a hot-pressing temperature range is determined, the hot-pressing temperature range is a temperature interval that ensures that the powder is fully melted and the fabric is not damaged;

[0150] Furthermore, based on the bonding strength requirement and the reaction rate of the raw material, a shearing time is determined, the shearing time is the shortest time to ensure that the raw material is fully mixed and reacted;

[0151] Furthermore, based on the raw material granularity and the mixing uniformity requirement, a stirring speed is determined, the stirring speed is the best speed to avoid raw material clumping and ensure uniform mixing;

[0152] Furthermore, the second matching result and the corresponding hot-pressing temperature, shearing time and stirring speed are integrated to generate a final matching scheme containing raw material proportion, process parameters and performance prediction value.

[0153] The embodiment of the police uniform adhesive lining powder matching system proposed in the present application extracts multi-dimensional core parameters through the demand analysis module, constructs a multi-objective matching scheme through the scheme generation module, completes parameter iterative optimization with the help of an intelligent matching model, outputs the final scheme by combining production process parameters through multi-dimensional adaptation evaluation and threshold screening, effectively solves the technical problem that the powder matching in the prior art relies on experience and is difficult to consider multiple demands, that is, the present application can not only realize precise matching for individualized demands such as police uniform fabric type and performance requirements, but also ensure the stability and reliability of the matching scheme through historical data and algorithm optimization, while considering environmental protection compliance and cost control, avoiding problems such as adhesion failure, poor washability or cost waste caused by improper matching.

[0154] The following describes an embodiment of a computer-readable storage medium proposed in this application. This computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements a method for mixing adhesive lining powder for police uniforms as described in any one of these embodiments.

[0155] The computer-readable storage medium proposed in this application stores a computer program for the corresponding police uniform adhesive lining powder mixing method, enabling the mixing method to be executed by a processor and applied to actual production scenarios. Its core advantage is consistent with the aforementioned police uniform adhesive lining powder mixing system: it can achieve precise mixing of adhesive powder under multiple requirements, balancing performance, environmental protection, and cost, and providing a standardized and replicable mixing scheme for police uniform production.

[0156] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0157] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the methods, apparatuses, and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0158] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between devices or modules may be electrical, mechanical, or other forms.

[0159] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0160] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0161] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0162] The computer program product includes one or more computer instructions. When the computer program is loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video optical disc), or a semiconductor medium (e.g., solid-state drive (SSD)).

[0163] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended embodiments and their equivalents.

Claims

1. A method for mixing adhesive powder for police uniform linings, applied to the precise mixing of adhesive powder for hot-melt adhesive linings of police uniforms, wherein the adhesive powder for police uniform linings comprises at least three or more combinations of matrix resin, curing agent, filler, and functional additives, characterized in that... include: Based on police uniform production demand data, obtain the core parameter set for the ratio. The production demand data is obtained in advance and includes at least the type of police uniform fabric, bonding strength standard, washability coefficient requirement, environmental protection index limit and usage environment conditions. Based on the core parameter set of the proportioning, a multi-objective proportioning scheme is generated. The proportioning scheme includes at least one or more combinations of the basic proportioning scheme, the performance optimization proportioning scheme, and the cost control proportioning scheme. Based on the aforementioned proportioning scheme, parameter iteration is performed in the intelligent proportioning model to obtain multiple first proportioning results; the intelligent proportioning model is pre-established based on a historical proportioning database and a multi-objective optimization algorithm; the historical proportioning database is pre-constructed based on historical formula data, performance test data, and raw material characteristic data of the adhesive lining powder for police uniforms; Obtain a first adaptation value that corresponds one-to-one with each first ratio result; the first adaptation value is used at least to characterize the degree of matching between the corresponding first ratio result and the core parameters of the production demand data, including the adhesion strength adaptation score, washability adaptation score, environmental compliance adaptation score, and cost adaptation score. Based on each first fit value, multiple second ratio results are obtained; The second ratio result is any first ratio result that meets the first preset condition, whereby the first preset condition is that the comprehensive score of the first fit value is not lower than a preset threshold. Based on the results of each second proportion, a final proportioning scheme is generated in combination with the production process parameters, which include at least the hot pressing temperature, shearing time, and stirring rate.

2. The method for mixing adhesive lining powder for police uniforms according to claim 1, characterized in that: The intelligent proportioning model includes a raw material characteristic extraction network, a parameter mapping network, and a multi-objective loss function network; The intelligent proportioning model is pre-established based on a historical proportioning database through the following methods: Based on the raw material feature extraction network, multidimensional feature codes are obtained from the raw material data in the historical proportioning database; the multidimensional feature codes include at least the viscosity characteristics of the matrix resin, the reactivity characteristics of the curing agent, the particle size distribution characteristics of the filler, and the functional characteristics of the additives. Based on the parameter mapping network, a set of proportioning parameter vectors is obtained by encoding the multidimensional features; the set of proportioning parameter vectors includes the weight percentage vector of each raw material, the performance prediction vector, and the cost vector; The final loss value is obtained from the matching parameter vector set based on the multi-objective loss function network. If the final loss value meets the second preset condition, the intelligent proportioning model is obtained based on the current raw material feature extraction network, parameter mapping network, and multi-objective loss function; otherwise, the weight parameters of the raw material feature extraction network and parameter mapping network are updated, and the final loss value is obtained again until the final loss value meets the second preset condition.

3. The method for mixing adhesive lining powder for police uniforms according to claim 2, characterized in that: The matching parameter vector set includes a first parameter vector group and a second parameter vector group; the first parameter vector group consists of positive sample matching vectors and negative sample matching vectors corresponding to different police uniform fabric types; the second parameter vector group is the optimal matching vector set under the same performance level requirements; obtaining the final loss value from the matching parameter vector set based on the multi-objective loss function network includes: Based on the first parameter vector group, the performance loss value is obtained; the performance loss value represents the adaptation deviation between the ratio scheme and the police uniform fabric type. Based on the second parameter vector group, the compliance loss value is obtained; the compliance loss value represents the deviation of the mixing scheme from the GA740-2007 standard and the VOC content limit standard. Based on the performance loss value and the compliance loss value, the final loss value is obtained.

4. The method for mixing adhesive lining powder for police uniforms according to claim 3, characterized in that: The process of obtaining the final loss value based on the performance loss value and the compliance loss value includes: Based on the first parameter vector group, a first performance matrix and a second performance matrix are obtained. The first performance matrix is ​​the performance detection result matrix for positive sample ratio vectors, and the second performance matrix is ​​the performance detection result matrix for negative sample ratio vectors. Based on the first performance matrix, a first total deviation is obtained; the first total deviation is used at least to characterize the difference between the positive sample matching scheme and the optimal performance index. Based on the second performance matrix, a second total deviation is obtained, which is used at least to characterize the difference between the negative sample matching scheme and the qualified performance index. Based on the sum of the first deviation and the sum of the second deviation, obtain the process adaptation loss value; The final loss value is obtained by weighted summation based on the performance loss value, the compliance loss value, and the process adaptation loss value.

5. A method for mixing adhesive lining powder for police uniforms according to any one of claims 1 to 4, characterized in that: The basic proportioning scheme includes: Based on the basic performance requirements in the core parameter group of the formulation, the benchmark formula with the highest matching degree is retrieved from the historical formulation database, and the proportion is finely adjusted according to the raw material characteristic parameters to obtain the basic formulation result. The basic performance requirements include at least peel strength ≥3.5N / 25mm and wash resistance coefficient ≥50 times. The performance optimization ratio scheme includes: Based on the high-performance requirements in the core parameter set of the formulation, the ratio of matrix resin to curing agent is optimized by response surface methodology, and the particle size distribution of filler and the amount of functional additives are adjusted to obtain the performance-optimized formulation results. The high-performance requirements include at least peel strength ≥ 5.0 N / 25 mm, wash resistance ≥ 100 cycles, and performance retention rate ≥ 90% after heat aging. The cost control allocation scheme includes: Based on the cost budget requirements of the core parameter set of the formulation, and on the premise of meeting the basic performance standards, the ratio of filler to matrix resin is optimized, and a cost-effective functional additive alternative is selected to obtain the cost control formulation result. The cost budget requirement is that the cost per unit weight of adhesive powder does not exceed a preset threshold.

6. The method for mixing adhesive lining powder for police uniforms according to claim 5, characterized in that: The process of generating a multi-objective proportioning scheme based on the core parameter set includes: Based on the core parameter set of the ratio, at least one second adaptation value is obtained. The second adaptation value is the degree of matching between the existing formulas in the historical ratio database and the core parameter set of the ratio. If an existing formula exists with a second fit value greater than or equal to the fit threshold, a basic formulation scheme is generated first. Otherwise, a combination of the basic formulation scheme and the performance-optimized formulation scheme is generated. If there are cost constraints, a cost-control formulation scheme is added.

7. The method for mixing adhesive lining powder for police uniforms according to claim 6, characterized in that: The step of obtaining the first fitting value corresponding one-to-one with each of the first ratio results includes: Based on each of the first proportion results, a third proportion result is obtained; the third proportion result is the current proportion scheme calculated in sequence from each of the first proportion results. Based on the third matching result, the matching score and weight coefficient of each dimension are obtained; the weight coefficient is set based on the priority in the production demand data, wherein the performance matching score weight is ≥0.5 in the high performance demand scenario, the environmental compliance matching score weight is ≥0.4 in the environmentally strict control scenario, and the cost matching score weight is ≥0.4 in the cost sensitive scenario. Based on the adaptation scores and weight coefficients of each dimension, the first adaptation value corresponding to the third matching result is obtained by weighted summation.

8. The method for mixing adhesive lining powder for police uniforms according to claim 7, characterized in that: After generating the final formulation, the method further includes: Obtain the actual production and testing data corresponding to the final formulation scheme; the actual production and testing data shall include at least the peel strength test value, the performance retention rate after washing, the VOC content test value, and the production qualification rate. Based on the actual production and testing data, an optimization adjustment coefficient corresponding to the final proportioning scheme is obtained; the optimization adjustment coefficient is used to correct the parameter mapping network of the intelligent proportioning model. Based on the optimized adjustment coefficients, the historical proportioning database of the intelligent proportioning model machine is updated. The update includes supplementing actual detection data, adjusting weight parameters, and optimizing loss function coefficients.

9. A system for mixing adhesive powder for police uniform linings, used for the precise mixing of adhesive powder in hot-melt linings of police uniforms, wherein the adhesive powder for police uniform linings comprises at least three or more combinations of matrix resin, curing agent, filler, and functional additives, characterized in that... include: The demand analysis module is used to obtain the core parameter set of the ratio based on the police uniform production demand data; The production demand data is acquired in advance, including at least the type of police uniform fabric, bonding strength standard, wash resistance requirements, environmental protection index limits, and usage environment conditions. The scheme generation module is used to generate a multi-objective proportioning scheme based on the core parameter set of the proportioning; the proportioning scheme includes at least any one or more combinations of the basic proportioning scheme, the performance optimization proportioning scheme, and the cost control proportioning scheme; The iterative calculation module is used to perform parameter iteration in the intelligent proportioning model based on the proportioning scheme to obtain multiple first proportioning results; the intelligent proportioning model is pre-established based on the historical proportioning database and multi-objective optimization algorithm; the historical proportioning database is pre-constructed based on the historical formula data, performance test data and raw material characteristic data of the adhesive lining powder for police uniforms; The adaptation evaluation module is used to obtain the first adaptation value that corresponds one-to-one with each first ratio result; the first adaptation value is used to characterize the degree of matching between the corresponding first ratio result and the core parameters in the production demand data, including the adhesion strength adaptation score, washability adaptation score, environmental compliance adaptation score and cost adaptation score. The scheme selection module is used to obtain multiple second matching ratio results based on each first fit value; The second ratio result is any first ratio result that meets the first preset condition, whereby the first preset condition is that the comprehensive score of the first fit value is not lower than a preset threshold. The final output module is used to generate a final proportioning scheme based on the results of each second proportioning and in combination with production process parameters; the production process parameters include at least hot pressing temperature, shearing time and stirring speed.

10. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements a method for mixing adhesive lining powder for police uniforms as described in any one of claims 1 to 8.

Images