Intelligent monitoring and control system for shoe production process

Abstract

The invention relates to the technical field of production process control, in particular to an intelligent monitoring and control system for a footwear production process, which comprises a footwear material parameter monitoring module, a footwear material state analysis module, a footwear material abnormity adjustment module and a footwear material resource optimization module. According to the method, key parameters in shoe material production are dynamically monitored and adjusted, production fine control and adaptability are improved, fluctuation data are recorded in real time, the trend is analyzed, the difference of the shoe material parameters under different production conditions is recognized, the consistency of the production state and the preset standard is ensured, and the production efficiency is improved. The production stability under the differentiated condition is optimized through classified induction of the fluctuation amplitude, the deviation frequency and amplitude are analyzed to support early prediction of abnormity, product quality fluctuation is avoided, and the product quality fluctuation is improved through accurate control over the temperature, the humidity and the compression strength, optimization of data feedback circulation and combination of resource demand analysis. The utilization efficiency of heat treatment, cooling and forming resources is improved, and efficient scheduling and high stability are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of production process control, and particularly to an intelligent monitoring and control system for the shoe production process. Background Art

[0002] The technical field of production process monitoring and control includes the real-time monitoring and feedback control of various process parameters in industrial production processes, aiming to optimize production quality, improve efficiency, and reduce resource waste. This field is applied in multiple industries. By collecting and processing key parameters in the production process, such as temperature, pressure, time, flow rate, etc., the state of equipment or systems is automatically adjusted. Such control systems rely on automation technologies and algorithms and can dynamically adapt to changes in production requirements to ensure product consistency and minimize human intervention, improving the stability and reliability of the overall production process.

[0003] Among them, the intelligent monitoring and control system for the shoe production process is an automated control system applied to the industrial manufacturing process, aiming to real-time monitor various key parameters in production and automatically adjust the operating state of production equipment according to preset control algorithms. The purpose of this system is to optimize the production process. Through data-driven feedback regulation, it ensures the consistency of product quality, production efficiency, and the optimization of resource utilization. Such systems can be widely applied in production fields that require high precision and high efficiency, such as the shoe manufacturing process, to achieve intelligent control by monitoring the specific indicators of each production process.

[0004] Although the prior art realizes the real-time monitoring and feedback control of parameters in the industrial production process, it lacks the dynamic classification and in-depth trend analysis of key parameters, resulting in the inability to fully adapt to the real-time changes in production requirements, and it is easy to generate a certain deviation accumulation under complex or special production conditions. In the prior art, parameter deviation monitoring is mainly based on fixed thresholds or single standards, which are difficult to accurately distinguish the types of fluctuations and cannot quickly adjust to cope with different types of abnormal trends, resulting in non-critical pauses or adjustment lags in the production process when facing sudden deviations. The resource allocation of the prior art focuses on the overall situation and lacks refined management of priorities. Therefore, in actual operation, the resource utilization efficiency is low, and it is easy to cause uneven equipment loads or resource waste. In application scenarios with high-precision and high-efficiency production requirements, the defects of the prior art lead to problems such as insufficient product consistency and sub-optimal resource allocation, and it is difficult to fully ensure the stability and adaptability of the production process. Summary of the Invention

[0005] The object of the present invention is to solve the disadvantages existing in the prior art, and to propose an intelligent monitoring and control system for the shoe production process.

[0006] To achieve the above object, the present invention adopts the following technical solution: An intelligent monitoring and control system for the shoe production process includes:

[0007] The shoe material parameter monitoring module records the fluctuations in the production stage and analyzes the change trend based on the heating temperature, humidity control, and compression strength in the shoe material production equipment, obtains the fluctuation range of the shoe material price, analyzes the differences in the shoe material price fluctuation range under different production conditions, determines the deviation from the set value, summarizes the deviation values and classifies them as key items, and obtains the shoe material deviation identification data;

[0008] The shoe material status analysis module analyzes the deviation frequency and amplitude based on the shoe material deviation identification data, summarizes the deviation changes, obtains the shoe material abnormal trend prediction data, refines and classifies the deviation sequence through the shoe material abnormal trend prediction data, extracts multiple types of deviation items, and forms a classified fluctuation analysis result;

[0009] The shoe material abnormal adjustment module extracts the adjustment value based on the classified fluctuation analysis result, calculates the deviation amplitude and correction data, adjusts the temperature, humidity, and compression strength, obtains the adjusted shoe material data, analyzes the numerical changes through the adjusted shoe material data, and obtains the shoe material stable parameter feedback data;

[0010] The shoe material resource optimization module analyzes the resource allocation requirements based on the shoe material stable parameter feedback data, calculates the priority sequence, calls the numerical values of heat treatment, cooling, and forming resources, and establishes a shoe material production deployment plan.

[0011] As a further solution of the present invention, the steps for obtaining the fluctuation range of the shoe material price are specifically as follows:

[0012] Based on the heating temperature, humidity control, and compression strength in the shoe material production equipment, extract the temperature change rate, humidity fluctuation range, and compression strength change frequency at each time node, analyze the fluctuation characteristics of each parameter at each time node, screen the time nodes with fluctuations exceeding the basic threshold as the initial screening set, and establish a production stage fluctuation range parameter set;

[0013] Based on the production stage fluctuation range parameter set, referring to the change characteristics of temperature, humidity, and compression strength, use the formula:

[0014]

[0015] Perform weighted calculation on the fluctuation ranges in the screening set to obtain the fluctuation range weight value, where W is the fluctuation range weight value, t i is the temperature change rate, h i is the humidity fluctuation range, s i is the compression strength change frequency, k 1 is the adjustment coefficient affected by humidity, k 2 is the influence ratio adjustment coefficient of temperature and humidity on the fluctuation range, and n is the number of time nodes in the initial screening set;

[0016] Based on the fluctuation amplitude weight value, compare it with the initial stability threshold to determine whether the fluctuation amplitude exceeds the range. If it exceeds, record it as an abnormal fluctuation to obtain the shoe material price fluctuation amplitude.

[0017] As a further solution of the present invention, the steps for obtaining the shoe material deviation identification data are specifically as follows:

[0018] Based on the shoe material price fluctuation amplitude, monitor the real-time changes of temperature, humidity, and compression strength under production conditions, record the temperature fluctuation value, humidity fluctuation amplitude, and compression strength change frequency at the time node, calculate the deviation for each parameter, extract the difference between the real-time monitored value and the set standard value, and generate a fluctuation differentiation data set for the shoe material production stage;

[0019] Call the fluctuation differentiation data set for the shoe material production stage, analyze the deviation values under each production condition, calculate the deviation amplitudes of temperature, humidity, and compression strength, and use the formula:

[0020]

[0021] Calculate the average deviation eigenvalue to obtain the deviation eigenvalue set of the shoe material production conditions, where D represents the average deviation eigenvalue, T, H, and S are the real-time temperature, humidity, and compression strength values respectively, T s 、H s 、S a are the standard set values, and M is the fluctuation amplitude weight adjustment coefficient;

[0022] Based on the deviation eigenvalue set of the shoe material production conditions, classify them according to the order of the deviation eigenvalues, screen the key deviation items, mark them as abnormal items, identify and mark the key deviations, and obtain the shoe material deviation identification data.

[0023] As a further solution of the present invention, the steps for obtaining the shoe material abnormal trend prediction data are specifically as follows:

[0024] Based on the shoe material deviation identification data, extract the deviation values for a time period, statistically summarize the deviation events in different time periods by analyzing the deviation frequency and amplitude parameters for each time period, record and calculate the numerical characteristics of the frequency and amplitude of the deviation occurrence, and generate a shoe material deviation frequency and amplitude characteristic set;

[0025] Call the shoe material deviation frequency and amplitude characteristic set, analyze the deviation frequency and amplitude item by item, and use the formula through the deviation amplitude change rate and frequency:

[0026]

[0027] Calculate the characteristic value of the change in shoe material deviation, where F represents the characteristic value of the change in shoe material deviation, A is the current deviation amplitude, A b is the reference deviation amplitude, B is the deviation occurrence frequency, C is the cumulative deviation amplitude in the current cycle, and d is the frequency fluctuation adjustment parameter;

[0028] Based on the characteristic value of the change in shoe material deviation, classify and analyze the trend changes according to different production conditions, extract abnormal trends and mark them to obtain shoe material abnormal trend prediction data.

[0029] As a further solution of the present invention, the steps for obtaining the classification fluctuation analysis result are specifically as follows:

[0030] According to the shoe material abnormal trend prediction data, select the fluctuation amplitude measured within the time window, judge whether it exceeds the range by comparing the difference between the absolute value of the fluctuation and the upper limit of the fluctuation, screen out the deviation items that do not exceed the upper limit, and generate a preliminary set of classified fluctuations;

[0031] Based on the preliminary set of classified fluctuations, calculate the multi-level characteristics of each deviation item. By the difference between the current deviation item and the classified fluctuation set, use the formula:

[0032]

[0033] Refine the classification of the fluctuations, establish the refined result of the classified fluctuations, where E represents the refined value of the classified fluctuations, V i represents the current value of the deviation item, M i represents the current interval mean of the fluctuation, W 1 、W 2 and W 3 are weight parameters, e represents the current interval length, and P is the deviation item characteristic parameter;

[0034] Match the refined result of the classified fluctuations with the fluctuation frequency of the deviation items item by item, set the frequency threshold through the stability of the fluctuation frequency, and judge the adaptability of the fluctuation items through the threshold, and eliminate the items that do not meet the threshold conditions to obtain the classification fluctuation analysis result.

[0035] As a further solution of the present invention, the steps for obtaining the adjusted shoe material data are specifically as follows:

[0036] Based on the classification fluctuation analysis result, extract the adjustment value, call the extracted adjustment value to calculate the fluctuation deviation under different conditions, and perform set operations through the adjustment factor parameters of temperature, humidity, and compression strength to obtain the fluctuation deviation adjustment parameter set;

[0037] According to the values in the fluctuation deviation adjustment parameter set, compare the initial shoe material data with the adjustment parameters, set the deviation amplitude threshold, analyze the values whose deviation amplitude exceeds the threshold, and use the formula:

[0038]

[0039] Generate adjustment deviation data, where G represents the adjustment deviation value, J represents the current temperature value, J 0 represents the temperature reference value, K represents the current humidity value, K 0 represents the humidity reference value, P represents the current compression strength, P 0 represents the compression strength reference value, U 1 and U 2 are the weight coefficients of humidity and compression strength respectively;

[0040] Based on the adjustment deviation data, adjust the shoe material parameters through the correction amplitude data of temperature, humidity, and compression strength, and generate the adjusted shoe material data.

[0041] As a further solution of the present invention, the acquisition steps of the shoe material stability parameter feedback data are specifically as follows:

[0042] Based on the adjusted shoe material data, extract the numerical change rate at each time point, calculate the change trend of each data point under different conditions, and summarize it into a shoe material change rate sequence to obtain the initial stability data;

[0043] Based on the initial stability data, calculate the change value of the key fluctuation threshold, extract the data values with large change fluctuations, and use the formula:

[0044]

[0045] Generate a shoe material stability fluctuation value sequence, where Q represents the shoe material stability fluctuation value, D v represents the initial stability data, k 3 and k 4 are weight coefficients, ΔP m represents the material pressure fluctuation, ω is the adjustment coefficient, R m represents the friction force parameter, T m is the material temperature parameter;

[0046] Use the shoe material stability fluctuation value sequence for cluster analysis, calculate the fluctuation average value according to the feedback stability parameters in the cluster results, and obtain the shoe material stability parameter feedback data by judging the consistency between the feedback stability parameters and the expected stability.

[0047] As a further solution of the present invention, the acquisition steps of the shoe material production deployment plan are specifically as follows:

[0048] Based on the feedback data of the shoe material stability parameters, extract the heat treatment, cooling, and forming requirement parameters related to resource allocation, analyze the resource allocation requirements in the production stage, calculate the initial allocation values of each resource, and generate an initial resource allocation plan;

[0049] Using the initial resource allocation plan, set the resource priority threshold according to the load values of the heat treatment, cooling, and forming resources. By calculating the resource load value and the allocation requirement, determine the priority of the resources in the production stage, using the formula:

[0050]

[0051] Generate a resource priority ranking, where Y is the resource priority value, R t is the heat treatment load, R c is the cooling requirement, R f is the forming load, α is the heat treatment weight, β is the cooling weight, γ is the forming resource adjustment coefficient, and θ is the production cycle coefficient;

[0052] Based on the resource priority ranking, combine the values of the heat treatment, cooling, and forming resources for allocation adjustment, map the resource allocation values to the priority ranking, and generate a shoe material production deployment plan.

[0053] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0054] In the present invention, by dynamically monitoring and adjusting the key parameters in shoe material production, the fine control and adaptability of the production process are improved. By real-time recording the fluctuation data of parameters such as heating temperature, humidity, and compression strength, and analyzing their change trends, the differences in shoe material parameters under different production conditions can be effectively identified, not only ensuring a high consistency between the shoe material production state and the preset standard, but also classifying and summarizing the fluctuation ranges, thereby optimizing the production stability under different conditions. The detailed analysis of the deviation frequency and amplitude provides data support for the early prediction and multi-level classification of shoe material anomalies, avoiding the risk of subsequent product quality fluctuations. In the adjustment link, by extracting the adjustment data for precise control of temperature, humidity, and compression strength, continuously optimizing the data feedback loop in the production process, further stabilizing the shoe material production output. Combining the analysis of resource requirements, optimizing the priority allocation of resources based on the feedback of shoe material stability parameters, thereby achieving the efficient utilization of heat treatment, cooling, and forming resources, making the production scheduling plan accurate and adaptable. This logic based on real-time feedback and multi-level control improves the consistency and resource utilization efficiency of shoe material production, ensures a high production stability, and significantly reduces the need for human intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is the system flow chart of the present invention;

[0056] Figure 2 It is a flowchart of the price fluctuation range of shoe materials in the present invention;

[0057] Figure 3 It is a flowchart of the deviation identification data of shoe materials in the present invention;

[0058] Figure 4 It is a flowchart of the abnormal trend prediction data of shoe materials in the present invention;

[0059] Figure 5 It is a flowchart of the classification fluctuation analysis result in the present invention;

[0060] Figure 6 It is a flowchart of the adjusted shoe material data in the present invention;

[0061] Figure 7 It is a flowchart of the feedback data of the shoe material stability parameter in the present invention;

[0062] Figure 8 It is a flowchart of the shoe material production deployment plan in the present invention. Detailed implementation manners

[0063] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0064] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more unless otherwise specifically defined.

[0065] Please refer to Figure 1 , an intelligent monitoring and control system for the shoe production process includes:

[0066] The shoe material parameter monitoring module records the fluctuations in the production stage and analyzes the change trend based on the heating temperature, humidity control, and compression strength in the shoe material production equipment, obtains the price fluctuation range of the shoe materials, analyzes the differences in the price fluctuation range of the shoe materials under different production conditions, determines the deviation from the set value, summarizes the deviation values and classifies them as key items, and obtains the deviation identification data of the shoe materials;

[0067] Based on the shoe material deviation identification data, the shoe material status analysis module analyzes the deviation frequency and amplitude, summarizes the deviation changes, obtains the prediction data of the abnormal trend of the shoe material, refines and classifies the deviation sequence through the prediction data of the abnormal trend of the shoe material, extracts multiple types of deviation items, and forms the classification fluctuation analysis result;

[0068] Based on the classification fluctuation analysis result, the shoe material abnormal adjustment module extracts the adjustment values, calculates the deviation amplitude and correction data, adjusts the temperature, humidity, and compression strength, obtains the adjusted shoe material data, and analyzes the numerical changes through the adjusted shoe material data to obtain the feedback data of the stable parameters of the shoe material;

[0069] Based on the feedback data of the stable parameters of the shoe material, the shoe material resource optimization module analyzes the resource allocation requirements, calculates the priority sequence, calls the numerical values of heat treatment, cooling, and forming resources, and establishes the production deployment plan for the shoe material.

[0070] The fluctuation range of the shoe material price includes the temperature fluctuation range, humidity fluctuation range, and compression strength fluctuation range. The shoe material deviation identification data includes the deviation type, deviation value, and key deviation items. The prediction data of the abnormal trend of the shoe material includes the abnormal frequency, abnormal amplitude, and trend direction. The classification fluctuation analysis result includes high-frequency deviation classification, medium-frequency deviation classification, and low-frequency deviation classification. The adjusted shoe material data includes the temperature adjustment value, humidity adjustment value, and strength adjustment value. The feedback data of the stable parameters of the shoe material includes the stable temperature value, stable humidity value, and stable strength value. The production deployment plan for the shoe material includes the heat treatment resource list, cooling resource list, and forming machine resource list.

[0071] Please refer to Figure 2 , and the specific steps for obtaining the fluctuation range of the shoe material price are as follows:

[0072] Based on the heating temperature, humidity control, and compression strength in the shoe material production equipment, extract the temperature change rate, humidity fluctuation range, and compression strength change frequency at each time node, analyze the fluctuation characteristics of each parameter at each time node, screen the time nodes with fluctuations exceeding the basic threshold as the initial screening set, and establish the fluctuation range parameter set of the production stage;

[0073] Based on the heating temperature, humidity control, and compression strength during the shoe material production process, extract the temperature change rate, humidity fluctuation range, and compression strength change frequency at each time node. First, record the temperature change value at each time node, calculate the temperature change rate per hour, and analyze whether the temperature change rate between adjacent time points meets the set temperature fluctuation threshold. Then, analyze the humidity. Record the humidity fluctuation range per hour as the humidity difference between adjacent moments, further calculate the humidity fluctuation rate, and determine the humidity change characteristics during the production process. For the compression strength, set the monitoring interval time for the compression strength, record the strength value at each monitoring moment, calculate the change frequency of the compression strength, and synchronize it with the temperature and humidity fluctuations to analyze the consistency at adjacent time nodes. Eliminate the fluctuation values that do not meet the consistency requirements, and thus form a parameter set of the temperature change rate, humidity fluctuation range, and compression strength change frequency in chronological order. Through one-by-one comparison and screening, obtain the fluctuation range parameter set for the production stage to analyze the fluctuation characteristics of the shoe material at each production stage.

[0074] Based on the fluctuation range parameter set for the production stage, referring to the change characteristics of temperature, humidity, and compression strength, use the formula:

[0075]

[0076] Perform a weighted calculation on the fluctuation ranges in the screening set to obtain the fluctuation range weight value. Among them, W is the fluctuation range weight value, t i is the temperature change rate, h i is the humidity fluctuation range, s i is the compression strength change frequency, k 1 is the adjustment coefficient affected by humidity, k 2 is the influence ratio adjustment coefficient of temperature and humidity on the fluctuation range, and n is the number of time nodes in the initial screening set;

[0077] The benefit of the formula is that through the combined analysis of the temperature change rate, humidity fluctuation range, and compression strength change frequency, the influence weights of humidity, temperature, and compression characteristics on the fluctuation range during the shoe material production process are more accurate;

[0078] t i represents the temperature change rate. Assume that the temperature change obtained by real-time collection through the equipment is 2.5 degrees per hour;

[0079] h i is the humidity fluctuation range, and the hourly change collected is 5%;

[0080] s i represents the compression strength change frequency. Assume that the change per hour is 1.2 times;

[0081] k 1is the humidity adjustment coefficient, set to 0.3; k 2 is the fluctuation amplitude adjustment coefficient, set to 2;

[0082] Substitute the values for the following calculations:

[0083] First, calculate

[0084] Then divide this value by n·k 2 , set n = 10:

[0085] The result shows that the overall fluctuation sensitivity of temperature, humidity, and pressure during the shoe material production process is a weight value of 0.7655. This value is the weight value of the shoe material price fluctuation amplitude and is used to analyze the fluctuation sensitivity of the shoe material under these process conditions.

[0086] Based on the weight value of the fluctuation amplitude, compare it with the initial stability threshold to determine whether the fluctuation amplitude exceeds the range. If it exceeds, record it as an abnormal fluctuation to obtain the shoe material price fluctuation amplitude;

[0087] Based on the comparison between the weight parameter of the fluctuation amplitude and the initial stability threshold, determine whether the fluctuation amplitude during the shoe material production process exceeds the preset stable range. First, extract the weight value of the fluctuation amplitude at each time node from the weight parameter of the fluctuation amplitude, compare it one by one with the set initial stability threshold to determine whether each time node meets the stability condition, mark the time nodes that do not meet the stability condition and record them in the non-compliant set. At the same time, record the specific fluctuation value and time node of the abnormal fluctuation point, further compare it with the value of the stable node, analyze the source of the abnormal fluctuation amplitude, establish a dataset of the fluctuation amplitude that exceeds the stable range. Through the analysis of this abnormal set, it helps to determine the fluctuation range during the shoe material production process.

[0088] Please refer to Figure 3 , the specific steps for obtaining the shoe material deviation identification data are as follows:

[0089] Based on the shoe material price fluctuation amplitude, monitor the real-time changes in temperature, humidity, and compression strength under the production conditions, record the temperature fluctuation value, humidity fluctuation amplitude, and compression strength change frequency at the time node, calculate the deviation for each parameter, extract the difference between the real-time monitored value and the set standard value, and generate a fluctuation differentiation dataset for the shoe material production stage;

[0090] Based on the fluctuation range of the shoe material production process, first use monitoring equipment to continuously collect the parameters of temperature, humidity, and compression strength during the production process, record the values at each time node, and ensure that the data covers all stages of the entire production process. To ensure the integrity and accuracy of the data, it is first necessary to preprocess the collected data, exclude abnormal data points caused by external interference or equipment failures, ensure that each recorded value meets the set equipment accuracy requirements, extract the fluctuations of each parameter at each time node, and obtain the temperature deviation, humidity deviation, and compression strength deviation at each time node by calculating the differences between the real-time temperature, humidity, and compression strength and the standard set values. Summarize the deviation values in the time series to form a complete differential data set for further calculation of deviation eigenvalue and critical judgment in the next step, and obtain the fluctuation differential data set of the shoe material production stage.

[0091] Call the fluctuation differential data set of the shoe material production stage, analyze the deviation values under each production condition, calculate the deviation amplitudes of temperature, humidity, and compression strength, and use the formula:

[0092]

[0093] Calculate the average deviation eigenvalue to obtain the deviation eigenvalue set of the shoe material production conditions. Among them, D represents the average deviation eigenvalue, T, H, and S are the real-time temperature, humidity, and compression strength values respectively, T s , H s , S a are the standard set values, and M is the fluctuation amplitude weight adjustment coefficient;

[0094] The benefit of the formula is that it unifies the fluctuation degrees of different physical quantities in a standardized expression through the weighted average method of the differences in temperature, humidity, and compression strength, which is convenient for comprehensive judgment and analysis;

[0095] In this formula, T is the real-time monitored temperature value, which is collected by a temperature sensor and read as 22 degrees Celsius, T s is the set standard temperature value of 20 degrees Celsius, H is the real-time collected humidity data, and the collected value is 50%, H s is the standard set humidity value of 45%, S is the real-time recorded compression strength value, which is recorded by a mechanical sensor as 30 MPa, S a is the standard set compression strength of 28 MPa, and M is the weight adjustment coefficient used to comprehensively adjust the influence of the deviation, with a value of 1. The following is the calculation process of substituting actual values:

[0096] Calculate the absolute value of the temperature difference: |T - T s | = |22 - 20| = 2;

[0097] Calculate the absolute value of the humidity difference: |H - H s | = |50 - 45| = 5;

[0098] Calculate the absolute value of the compressive strength difference: |S - S a | = |30 - 28| = 2;

[0099] Comprehensively calculate the deviation eigenvalue D:

[0100] This result shows that under the current production conditions, the deviation eigenvalue is 3, which reflects the average deviation between the temperature, humidity, and pressure values of the actual production conditions and the set standards, serving as the basic data for screening key deviation items in subsequent steps.

[0101] Based on the set of deviation eigenvalues of the shoe material production conditions, classify them in the order of deviation eigenvalues, screen key deviation items, mark them as abnormal items, identify and mark key deviations, and obtain shoe material deviation identification data;

[0102] Based on the set of deviation eigenvalues of the shoe material production conditions, arrange the deviation eigenvalues of each production condition from smallest to largest, classify them according to the numerical range of the deviation, identify the data points with larger deviations among them, classify them as key deviation items, record the numerical characteristics of the key deviation items, specifically including the time nodes, deviation amplitudes, and actual measured values of temperature, humidity, and compressive strength for each item, summarize the characteristics of each key deviation item in detail and mark it, identify significant fluctuations in the shoe material production process, provide data support for further analyzing the impact of production conditions on the performance of shoe materials, and obtain shoe material deviation identification data.

[0103] Please refer to Figure 4 , the steps for obtaining shoe material abnormal trend prediction data are specifically as follows:

[0104] Based on the shoe material deviation identification data, extract the deviation values for the time period, statistically analyze and summarize the deviation events in different time periods by analyzing the deviation frequency and amplitude parameters for each period, record and calculate the numerical characteristics of the frequency and amplitude of the deviation occurrence, and generate a set of shoe material deviation frequency and amplitude characteristics;

[0105] Based on the shoe material deviation identification data, extract the deviation values for each production time period, analyze and record the deviation data one by one. By analyzing the deviation frequency for each time period, that is, the number of times the deviation occurs, and calculating the numerical amplitude of each deviation, gradually form complete statistical data, including the deviation frequency and amplitude data for all production time periods. Combine the parameter value changes within each time period, mark the deviations with higher frequencies additionally to distinguish ordinary deviations and high-frequency deviations, and finally summarize the numerical characteristics of the deviations for each time period to generate a set of shoe material deviation frequency and amplitude characteristics, laying a data foundation for subsequent detailed analysis.

[0106] Call the feature set of the deviation frequency and amplitude of the shoe material, analyze the deviation frequency and amplitude item by item, and adopt the formula through the change rate and frequency of the deviation amplitude:

[0107]

[0108] Calculate the characteristic value of the shoe material deviation change. Among them, F represents the characteristic value of the shoe material deviation change, A is the current deviation amplitude, A b is the reference deviation amplitude, B is the deviation occurrence frequency, C is the cumulative deviation amplitude in the current cycle, and d is the frequency fluctuation adjustment parameter;

[0109] The benefit of the formula is that by introducing the combined operation of the frequency and amplitude adjustment parameters, the relationship between the deviation frequency and amplitude is optimized, which helps to more accurately reflect the deviation change trend of the shoe material in different time periods;

[0110] Among them, A is the current deviation amplitude, which is obtained by extracting the deviation data 15, A b is the reference deviation amplitude in the previous time period, which is 12, B represents the deviation occurrence frequency, which is counted as 3 times in the current time period, C is the cumulative deviation amplitude in the current cycle, and the cumulative value is 25, d is the frequency fluctuation adjustment parameter, taking 5, and substituting it into the formula for calculation as follows:

[0111] Calculate the absolute difference between the current and reference deviation amplitudes: |A - A b | = |15 - 12| = 3;

[0112] Multiply by the frequency B: 3·3 = 9;

[0113] Calculate the square root part of the denominator:

[0114] Finally, calculate the deviation change characteristic value F:

[0115] The result shows that the deviation change characteristic value in the current time period is 1.642, which reflects the comprehensive deviation of the frequency and amplitude in the shoe material production process at this time, and provides a reference for the subsequent abnormal trend analysis.

[0116] Based on the characteristic value of the shoe material deviation change, classify and analyze the trend change according to the differential production conditions, extract the abnormal trend and mark it, and obtain the shoe material abnormal trend prediction data;

[0117] Based on the set of characteristic values ​​of shoe material deviation changes, the deviation characteristic values ​​in different time periods are first classified according to production conditions. Through careful comparison, the deviation amplitude and frequency changes under different conditions are found, and the time periods with larger deviation characteristic values ​​are selected. At the same time, the deviation data in the time period are compared one by one, and the time points with abnormal fluctuation amplitude are extracted and marked as key deviation intervals. For the time periods in which the deviation values ​​are continuously higher than the benchmark threshold, further records are made, and the deviation change characteristic values ​​of the time period are gradually accumulated to sort out the overall trend. In the sorting process, the data needs to be subdivided and summarized, and the actual parameters and deviation characteristic values ​​of each time period are recorded to ensure data integrity. Finally, the time periods with higher abnormal deviation values ​​and frequencies are marked and summarized to generate shoe material abnormal trend prediction data, which provides support for subsequent production monitoring and real-time adjustments.

[0118] See also Figure 5 , the specific steps for obtaining the classification fluctuation analysis results are:

[0119] According to the abnormal trend prediction data of shoe materials, the fluctuation amplitude measured in the selected time window is compared with the difference between the absolute value of the fluctuation and the upper limit of the fluctuation to determine whether it exceeds the range, and the deviation items that do not exceed the upper limit are screened to generate a preliminary set of classified fluctuations;

[0120] According to the abnormal trend prediction data of shoe materials, each deviation item in the deviation sequence is called, and the fluctuation amplitude of the deviation item in the selected time window is calculated one by one. By calculating the difference between the absolute value of the fluctuation value and the set upper limit of the fluctuation, it is judged whether the current deviation item exceeds the upper limit range. If it exceeds, the deviation item is eliminated. If it does not exceed, it is retained in the preliminary set. After all deviation items are processed step by step, the deviation items that meet the requirements are summarized into the classified fluctuation preliminary set, which contains all deviation items whose fluctuation range meets the requirements in the current time window.

[0121] Based on the preliminary set of classified fluctuations, the multi-level features of each deviation item are calculated, and the formula is used based on the difference between the current deviation item and the classified fluctuation set:

[0122]

[0123] The fluctuations are classified and classified, and the classification fluctuations are refined. E represents the classification fluctuation refinement value, V i Represents the current value of the deviation term, M i represents the current interval mean of fluctuation, W 1 , W 2 and W 3 is the weight parameter, e represents the current interval length, and P is the characteristic parameter of the deviation term;

[0124] The benefit of the formula is to amplify or reduce the differences of different deviation terms by using multiple weight parameters, so as to enhance the fine classification effect of the deviation terms and improve the accuracy of refined classification;

[0125] Set the current value V of the deviation term i = 10, the fluctuation mean value M i = 8, the weight parameter W 1 = 1.2, W 2 = 0.5, W 3 = 0.3, the interval length e = 4, the feature parameter P = 2;

[0126] First, calculate the absolute difference of the numerator part multiplied by the weight:

[0127] |V i - M i |·W 1 = |10 - 8|·1.2 = 2·1.2 = 2.4

[0128] Then, calculate the square root of the denominator plus the adjustment part:

[0129]

[0130] Finally, calculate the formula E:

[0131]

[0132] This result shows that the classification fluctuation refinement value is 1.083, indicating the degree of fluctuation difference between the current deviation term and the set. Through this refinement classification value, the adaptability of classification fluctuation can be further analyzed in the follow-up.

[0133] Match the classification fluctuation refinement result with the fluctuation frequency of the deviation term item by item, set the frequency threshold through the stability of the fluctuation frequency, and judge the adaptability of the fluctuation term through the threshold, and eliminate the items that do not meet the threshold conditions to obtain the classification fluctuation analysis result;

[0134] Match the classification fluctuation refinement result with the fluctuation frequency of each deviation term item by item. By analyzing the stability of the current fluctuation frequency item by item, screen out and eliminate the deviation terms with the fluctuation frequency exceeding the set threshold from the set, retain the deviation terms that meet the frequency stability conditions, and at the same time set the stability threshold during the screening process. Judge whether the deviation terms that meet the conditions are adaptable to the target conditions through continuous multiple comparisons, and summarize all the deviation terms that meet the conditions to form the classification fluctuation analysis result.

[0135] Please refer to Figure 6 , the specific steps for obtaining the adjusted shoe material data are as follows:

[0136] Extract the adjustment value based on the classification fluctuation analysis result, call the extracted adjustment value to calculate the fluctuation deviation under different conditions, and perform a set operation through the adjustment factor parameters of temperature, humidity, and compression strength to obtain the fluctuation deviation adjustment parameter set;

[0137] Extract the adjustment value based on the classification fluctuation analysis result, combine the actual measurement data of temperature, humidity, and compression strength, decompose and record the fluctuation characteristics under different conditions item by item, and further calculate the overall fluctuation amplitude of these data by summarizing the numerical deviations of each adjustment factor. First, classify and extract the fluctuations corresponding to each adjustment parameter according to the classification result, screen the main fluctuation factors from the temperature, humidity, and compression strength parameters, organize the data into a fluctuation amplitude set, and based on the parameter set, calculate the fluctuation deviation under specific adjustment conditions to obtain the deviation amplitude data set of temperature, humidity, and compression strength. Then, compare the values in the deviation amplitude set item by item to identify the main fluctuation regions of each adjustment parameter, analyze the influence of the fluctuation characteristics of each parameter by establishing the correlation between temperature, humidity, and compression strength, combine the data under specific adjustment conditions to form an overall fluctuation deviation adjustment parameter set, and finally merge the fluctuation amplitude sets under different conditions.

[0138] According to the values in the fluctuation deviation adjustment parameter set, compare the initial data of the shoe material with the adjustment parameters, set the deviation amplitude threshold, and analyze the values whose deviation amplitude exceeds the threshold. Through the formula:

[0139]

[0140] Generate the adjustment deviation data, where G represents the adjustment deviation value, J represents the current temperature value, J 0 represents the temperature reference value, K represents the current humidity value, K 0 represents the humidity reference value, P represents the current compression strength, P 0 represents the compression strength reference value, U 1 and U 2 are the weight coefficients of humidity and compression strength respectively;

[0141] The advantage of the formula is that by introducing different weight coefficients U 1 and U 2 , the influence degrees of humidity and compression strength are differentially adjusted, thus enhancing the flexibility of the comprehensive adjustment deviation calculation;

[0142] Set the temperature J to 25 °C, the temperature reference value J 0 is 20 °C, set the humidity K to 60%, the humidity reference value K 0 is 50%, set the compression strength P to 500 MPa, the compression strength reference value P 0 is 450 MPa, the weight coefficient U1 and U 2 are set to 0.8 and 0.6 respectively;

[0143] Substitute the above values and calculate each item:

[0144]

[0145] Add up each item and take the square root to get:

[0146]

[0147] This result shows that the comprehensive adjustment deviation is 1.8594. Through this value, the deviation amplitude of each parameter after adjustment can be further analyzed.

[0148] Based on the adjustment deviation data, adjust the shoe material parameters through the correction amplitude data of temperature, humidity, and compression strength to generate the adjusted shoe material data;

[0149] Based on the comprehensive adjustment deviation data, first analyze the comprehensive adjustment deviation data, compare the specific data of the deviation amplitude with the initial value of the adjusted shoe material parameters. After comparing the deviation amplitude of the temperature parameter item by item with the reference data, adjust the current temperature value step by step according to the deviation value to ensure that the temperature deviation is within the control range. Then substitute the deviation amplitude data into the humidity parameter, compare with the reference humidity value, and control the deviation amplitude of the humidity within the set range. Then adjust the compression strength deviation according to the comprehensive deviation data, control the deviation amplitude of the compression strength, and adjust each parameter step by step to approach the reference value. Finally, merge all the adjusted temperature, humidity, and compression strength values to form the adjusted shoe material data.

[0150] Please refer to Figure 7 , the specific steps for obtaining the feedback data of the shoe material stability parameters are as follows:

[0151] Based on the adjusted shoe material data, extract the numerical change rate at each time point, calculate the change trend of each data point under different conditions, and summarize it into a shoe material change rate sequence to obtain the initial stability data;

[0152] Based on the adjusted shoe material data, extract the rate of change of the numerical values in the time series. By setting the time interval and conditions, analyze the change amount of the numerical values at different time points one by one and form a rate of change sequence. First, perform basic cleaning on the data to remove outliers or noise interference values. Use the cleaned data to determine the change trend of the shoe material under various environmental conditions. Calculate the rate of change of the numerical value at each data point according to the time interval of each data point, and form a rate of change sequence of the shoe material in combination with this rate of change. Conduct further preliminary analysis on this sequence to obtain a reference basis for stability evaluation. Use the rate of change sequence summarized from the above-mentioned rate of change analysis results as the rate of change sequence of the shoe material to obtain the initial stability data.

[0153] Based on the initial stability data, calculate the change value of the key fluctuation threshold, and extract the data values with large change fluctuations. Use the formula:

[0154]

[0155] Generate a sequence of shoe material stability fluctuation values. Among them, Q represents the shoe material stability fluctuation value, D v represents the initial stability data, k 3 and k 4 are weight coefficients, ΔP m represents the material pressure fluctuation, ω is the adjustment coefficient, R m represents the friction parameter, T m is the material temperature parameter;

[0156] The advantage of the formula is that it calculates the shoe material stability fluctuation by involving multiple influencing factors. Combining the pressure fluctuation, friction, and temperature parameters, it improves the multidimensionality of the calculation without changing the basic structure of the formula;

[0157] The initial stability data D v = 5 (obtained through material stress testing), the pressure fluctuation ΔP m = 2 (measured based on the data of the shoe material under different pressure-bearing conditions), the friction parameter R m = 3 (collected through the friction coefficient and surface contact analysis data), the temperature parameter T m = 7 (obtained based on the temperature records under environmental conditions);

[0158] The weight parameters k 3 and k 4 are respectively set to 0.8 and 1.2, the adjustment coefficient ω = 4 (for the comprehensive evaluation of the shoe material characteristics and environmental conditions), and substitute into the formula:

[0159]

[0160] Q = |5 + 1.6 + 1.2·3.464 - 7|

[0161] Q = |5 + 1.6 + 4.157 - 7|

[0162] Q = |3.757| = 3.757

[0163] This result indicates that the stability fluctuation value of the shoe material is 3.757, which characterizes the comprehensive fluctuation level of the shoe material under various load and temperature fluctuation conditions, providing a quantitative basis for further stability analysis.

[0164] Using the sequence of stability fluctuation values of the shoe material, perform cluster analysis, calculate the average fluctuation value according to the feedback stability parameters in the clustering results, and obtain the feedback data of the shoe material stability parameters by judging the consistency between the feedback stability parameters and the expected stability.

[0165] Using the sequence of stability fluctuation values of the shoe material, conduct cluster classification for each fluctuation value, extract the feedback stability parameters with relatively low stability in each category according to the classification results, calculate the average value of the fluctuations of the parameters, ensure that the average value of the fluctuations within each clustering category can characterize its stability characteristics, and by setting the expected stability threshold, judge whether each feedback stability parameter is within the threshold range. If it meets the expectation, it means that the feedback stability parameter has stability under actual application conditions. Through the above cluster analysis and threshold determination, the feedback data of the shoe material stability parameters are finally obtained.

[0166] Please refer to Figure 8 , the specific steps for obtaining the production deployment plan of the shoe material are as follows:

[0167] Based on the feedback data of the shoe material stability parameters, extract the heat treatment, cooling, and forming demand parameters related to resource allocation, analyze the resource configuration requirements in the production stage, calculate the initial allocation value of each resource, and generate an initial resource allocation plan.

[0168] Based on the feedback data of the shoe material stability parameters, extract the various resource demand indicators involved in resource allocation. First, obtain the specific requirements for heat treatment, cooling, and forming resources in the production stage to ensure that the configuration of each resource meets the requirements of each production stage. For the parameters of different processes, analyze their direct impact on resource allocation, calculate the preliminary demand value of the resources according to the production data monitoring and feedback data, and subdivide the resource demand through the specific values in the allocation plan, including dynamically adjusting the resource demand at different time periods according to the feedback data. At the same time, evaluate the existing load situation of each resource. First, compare the production requirements and feedback data of each stage, and calculate the resource load item by item based on the comparison results to form a basic allocation value that meets the actual requirements. The generated initial resource allocation plan provides a preliminary reference for the next resource priority ranking and dynamic allocation.

[0169] Using the initial resource allocation plan, set the resource priority threshold according to the load values of heat treatment, cooling, and forming resources. Determine the priority of resources in the production stage through the calculation of resource load values and allocation requirements, using the formula:

[0170]

[0171] Generate the resource priority ranking, where Y is the resource priority value, and R t is the heat treatment load, R c is the cooling requirement, R f is the forming load, α is the heat treatment weight, β is the cooling weight, γ is the forming resource adjustment coefficient, and θ is the production cycle coefficient;

[0172] The advantage of the formula is that it combines the load values and allocation requirements of each resource, and sets weight parameters and adjustment coefficients according to the priority requirements of each resource, making the priority ranking more accurate;

[0173] Collect the heat treatment resource load R t = 12, and determine the actual demand for heat treatment resources in the current production process through equipment load data;

[0174] Collect the cooling resource requirement R c = 8, and conduct a demand analysis for the allocation of cooling resources according to different stages of the cooling process, and set the load value;

[0175] The forming resource load R f = 15, combined with the operation requirements and load measurement of the forming equipment;

[0176] Set the production cycle coefficient θ = 1.2, determined by analyzing the equipment operation status of this cycle;

[0177] Weight setting: The heat treatment weight α = 0.75, set a higher priority according to the impact of heat treatment on the overall production process. The cooling resource weight β = 1.1, evaluate the allocation based on the load requirements and production cycle of the cooling stage. The forming resource adjustment coefficient γ = 0.6, and give an appropriate adjustment coefficient by analyzing the adaptability of the forming resources;

[0178] Substitute into the formula:

[0179]

[0180] Y = |9 + 7.27 + 3.29|

[0181] Y = |19.56| = 19.56

[0182] This result shows that the priority value is 19.56, providing the priority ranking of resources in the production stage and laying a numerical basis for the resource priority ranking scheme.

[0183] Based on the resource priority ranking, combined with the numerical values of heat treatment, cooling, and forming resources for allocation adjustment, map the resource allocation numerical values to the priority ranking to generate a production deployment plan for shoe materials;

[0184] Based on the priority ranking scheme, call the numerical values of heat treatment, cooling, and forming resources required in each stage, allocate the resource quantities according to the priority sequence, first match the requirements of each resource in the production stage, ensure that the resources are allocated item by item to different production stages according to the priority, map the priority data obtained from the ranking scheme to the resource allocation quantity, dynamically optimize the numerical values in the resource allocation process, use the real-time monitored data to update the priority ranking, dynamically analyze the current load status and the completion degree of production tasks, and establish a production deployment plan for shoe materials by performing real-time allocation of the resource requirements in different stages.

[0185] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent monitoring and control system for a footwear production process, characterized in that: The system comprises: The shoe material parameter monitoring module records the fluctuations in the production stage and analyzes the changing trends based on the heating temperature, humidity control, and compression strength in the shoe material production equipment, obtains the price fluctuation range of the shoe material, analyzes the difference in the price fluctuation range of the shoe material under differentiated production conditions, determines the deviation from the set value, summarizes the deviation values ​​and classifies them into key items, and obtains shoe material deviation identification data; The shoe material state analysis module analyzes the deviation frequency and amplitude based on the shoe material deviation identification data, summarizes the deviation changes, obtains shoe material abnormal trend prediction data, refines and classifies the deviation sequence through the shoe material abnormal trend prediction data, extracts multiple categories of deviation items, and forms a classification fluctuation analysis result; The shoe material abnormal adjustment module extracts the adjustment value based on the classification fluctuation analysis result, calculates the deviation amplitude and correction data, adjusts the temperature, humidity, and compression strength, obtains the adjusted shoe material data, analyzes the value change through the adjusted shoe material data, and obtains the shoe material stability parameter feedback data; The shoe material resource optimization module analyzes resource allocation requirements, calculates priority sequences, calls heat treatment, cooling and molding resource values, and establishes a shoe material production deployment plan based on the shoe material stability parameter feedback data.

2. The intelligent monitoring and control system for the footwear production process according to claim 1 is characterized in that: The steps for obtaining the fluctuation range of the shoe material price are specifically as follows: Based on the heating temperature, humidity control, and compression strength in the shoe material production equipment, the temperature change rate, humidity fluctuation amplitude, and compression strength change frequency at each time node are extracted, the fluctuation characteristics of each parameter at each time node are analyzed, and the time nodes whose fluctuations exceed the basic threshold are selected as the initial screening set to establish the fluctuation amplitude parameter set for the production stage; Based on the fluctuation amplitude parameter set of the production stage, referring to the variation characteristics of temperature, humidity and compression strength, the formula is adopted: The fluctuation range in the screening set is weighted to obtain the fluctuation range weight value, where W is the fluctuation range weight value, t i is the temperature change rate, h i is the humidity fluctuation amplitude, s i is the frequency of compression strength change, k1 is the adjustment coefficient of humidity, k2 is the proportional adjustment coefficient of the influence of temperature and humidity on the fluctuation amplitude, and n is the number of time nodes in the initial screening set; Based on the fluctuation amplitude weight value, it is compared with the initial stability threshold to determine whether the fluctuation amplitude exceeds the range. If it exceeds the range, it is recorded as an abnormal fluctuation to obtain the fluctuation amplitude of the shoe material price.

3. The intelligent monitoring and control system for the footwear production process according to claim 2 is characterized in that: The steps for obtaining the shoe material deviation identification data are specifically as follows: Based on the price fluctuation range of the shoe materials, monitor the real-time changes of temperature, humidity and compression strength under production conditions, record the temperature fluctuation value, humidity fluctuation range and compression strength change frequency at the time node, perform deviation calculation for each parameter, extract the difference between the real-time monitoring value and the set standard value, and generate a fluctuation differentiation data set for the shoe material production stage; The fluctuation differentiation data set of the shoe material production stage is called, the deviation value under each production condition is analyzed, and the deviation amplitude of temperature, humidity and compression strength is calculated using the formula: Calculate the average deviation characteristic value and obtain the deviation characteristic value set of shoe material production conditions, where D represents the average deviation characteristic value, T, H, and S are the real-time temperature, humidity, and compression strength values, respectively, and T s , H s , S a is the standard setting value, M is the fluctuation range weight adjustment coefficient; Based on the deviation characteristic value set of the shoe material production conditions, the deviation characteristic values ​​are classified in order, key deviation items are screened and marked as abnormal items, key deviations are identified and marked, and shoe material deviation identification data is obtained.

4. The intelligent monitoring and control system for the footwear production process according to claim 3 is characterized in that: The steps for obtaining the abnormal trend prediction data of shoe materials are specifically as follows: Based on the shoe material deviation identification data, the deviation values ​​of the time period are extracted, and by analyzing the deviation frequency and amplitude parameters of each time period, the deviation events of the differentiated time periods are counted and summarized, and the numerical characteristics of the frequency and amplitude of the deviation are recorded and calculated to generate a shoe material deviation frequency and amplitude feature set; The shoe material deviation frequency and amplitude feature set is called, and the deviation frequency and amplitude are analyzed item by item. The formula is used through the deviation amplitude change rate and frequency: The shoe material deviation change characteristic value is calculated, where F represents the shoe material deviation change characteristic value, A is the current deviation amplitude, and A b is the reference deviation amplitude, B is the frequency of deviation, C is the cumulative deviation amplitude in the current cycle, and d is the frequency fluctuation adjustment parameter; Based on the shoe material deviation change characteristic value, the trend changes are classified and analyzed according to differentiated production conditions, abnormal trends are extracted and marked, and shoe material abnormal trend prediction data is obtained.

5. The intelligent monitoring and control system for the footwear production process according to claim 4, characterized in that: The steps for obtaining the classification fluctuation analysis results are specifically as follows: According to the abnormal trend prediction data of the shoe material, the fluctuation amplitude measured in the time window is selected, and by comparing the difference between the absolute value of the fluctuation and the upper limit of the fluctuation, it is determined whether it exceeds the range, and the deviation items that do not exceed the upper limit are screened to generate a preliminary set of classified fluctuations; Based on the preliminary set of classified fluctuations, the multi-level features of each deviation item are calculated, and the formula is used according to the difference between the current deviation item and the classified fluctuation set: The fluctuations are classified and classified, and the classification fluctuations are refined. E represents the classification fluctuation refinement value, V i Represents the current value of the deviation term, M i represents the current interval mean of the fluctuation, W1, W2 and W3 are weight parameters, e represents the current interval length, and P is the characteristic parameter of the deviation term; The classification fluctuation refinement result is matched with the fluctuation frequency of the deviation item one by one, the frequency threshold is set according to the stability of the fluctuation frequency, and the adaptability of the fluctuation item is judged by the threshold, and the items that do not meet the threshold conditions are eliminated to obtain the classification fluctuation analysis result.

6. The intelligent monitoring and control system for the footwear production process according to claim 5, characterized in that: The steps for obtaining the adjusted shoe material data are specifically as follows: Extracting adjustment values ​​based on the classification fluctuation analysis results, calling the extracted adjustment values ​​to calculate the fluctuation deviation under differentiated conditions, and performing set operations on adjustment factor parameters of temperature, humidity, and compression strength to obtain a fluctuation deviation adjustment parameter set; According to the values ​​in the fluctuation deviation adjustment parameter set, the initial data of the shoe material is compared with the adjustment parameters, a deviation amplitude threshold is set, and the values ​​of the deviation amplitude exceeding the threshold are analyzed, and the formula is used: Generate adjustment deviation data, where G represents the adjustment deviation value, J represents the current temperature value, J0 represents the temperature reference value, K represents the current humidity value, K0 represents the humidity reference value, P represents the current compression strength, P0 represents the compression strength reference value, and U1 and U2 are weight coefficients of humidity and compression strength respectively; Based on the adjustment deviation data, the shoe material parameters are adjusted through the correction amplitude data of temperature, humidity and compression strength to generate adjusted shoe material data.

7. The intelligent monitoring and control system for the footwear production process according to claim 6, characterized in that: The steps for obtaining the feedback data of the shoe material stability parameter are specifically as follows: Based on the adjusted shoe material data, extract the value change rate at each time point, calculate the change trend of each data point under differentiated conditions, and summarize them into a shoe material change rate sequence to obtain initial stability data; Based on the initial stability data, calculate the change value of the key fluctuation threshold, extract the data value with large fluctuation, and use the formula: Generate a sequence of shoe material stability fluctuation values, where Q represents the shoe material stability fluctuation value, D v represents the initial stability data, k3 and k4 are weight coefficients, ΔP m represents the material pressure fluctuation, ω is the adjustment coefficient, R m represents the friction parameter, T m is the material temperature parameter; The shoe material stability fluctuation value sequence is used to perform cluster analysis, and the fluctuation average value is calculated according to the feedback stability parameter in the clustering result. The shoe material stability parameter feedback data is obtained by judging the consistency between the feedback stability parameter and the expected stability.

8. The intelligent monitoring and control system for the footwear production process according to claim 7, characterized in that: The steps for obtaining the shoe material production deployment plan are specifically as follows: Based on the feedback data of the shoe material stability parameters, the heat treatment, cooling and molding requirement parameters associated with resource allocation are extracted, and the resource allocation requirements in the production stage are analyzed, the initial allocation value of each resource is calculated, and an initial resource allocation plan is generated; Using the initial resource allocation scheme, according to the load values ​​of heat treatment, cooling and forming resources, the resource priority threshold is set, and the priority of resources in the production stage is determined by calculating the resource load value and allocation demand, using the formula: Generate resource priority ranking, where Y is the resource priority value, R t is the heat treatment load, R c is the cooling demand, R f is the molding load, α is the heat treatment weight, β is the cooling weight, γ is the molding resource adjustment coefficient, and θ is the production cycle coefficient; Based on the resource priority ranking, the allocation adjustment is performed in combination with the values ​​of heat treatment, cooling and molding resources, the resource allocation values ​​are mapped with the priority ranking, and a shoe material production deployment plan is generated.

Images