Intelligent optimization method and system for processing parameters of electronic auxiliary materials

Abstract

The present invention relates to the field of intelligent manufacturing, and discloses an intelligent optimization method and system for processing parameters of electronic auxiliary materials, including: firstly obtaining electronic auxiliary materials to be processed, clarifying the corresponding initial processing parameters, collecting real-time operation data of preset processing equipment accordingly, obtaining classified data sets through classification processing, extracting core parameter subsets, and then generating processing process curves of core parameter subsets, analyzing slopes to obtain slope change sequences, finding mutation points and calculating mutation impact values, collecting fluctuation characteristics associated therewith, clarifying fluctuation ranges in different processing stages, calculating auxiliary material stability values, thereby determining processing directions, identifying corresponding processing adjustment strategies, monitoring effect data in real time after implementing strategies, comparing with preset target data to obtain effect comparison parameters, and then querying potential improvement factors, determining improvement levels, setting level indicators, and finally generating optimization schemes adapted to electronic auxiliary materials to be processed. The present invention can improve the production efficiency of electronic auxiliary materials.

Description

Technical Field

[0001] The invention relates to an intelligent optimization method and system for processing parameters of electronic auxiliary materials, belonging to the field of intelligent manufacturing. Background Art

[0002] In today's highly industrialized era, the electronics industry, as the core driving force for the development of science and technology, is booming at an unprecedented rate. Electronic accessories are an indispensable part of electronic product manufacturing, and their processing quality is directly related to the performance and quality of the final electronic products. From sophisticated smartphones to large-scale server equipment, the stable operation of each electronic component is inseparable from the support of high-quality electronic accessories.

[0003] At present, the traditional method of setting processing parameters for electronic auxiliary materials has gradually revealed its shortcomings in response to increasingly complex production needs. On the one hand, most of the previous processing parameters were determined by empirical values. There are slight differences in the characteristics of raw materials in different batches, such as the viscosity of electronic slurry, the distribution density of conductive particles, etc. These differences will result in the inability to achieve the optimal performance of the auxiliary materials when processed according to fixed empirical parameters, and the product yield is difficult to guarantee. On the other hand, in the traditional processing process, parameter adjustment lacks real-time and accuracy. When faced with dynamic factors such as changes in temperature and humidity in the production environment and aging and wear of equipment, the processing parameters cannot be adaptively optimized in time, resulting in low production efficiency of electronic auxiliary materials. Therefore, an intelligent optimization method for processing parameters of electronic auxiliary materials is needed to improve the production efficiency of electronic auxiliary materials. Summary of the invention

[0004] The present invention provides an electronic auxiliary material processing parameter intelligent optimization method and system, the main purpose of which is to improve the production efficiency of electronic auxiliary materials.

[0005] To achieve the above-mentioned purpose, the present invention provides an intelligent optimization method for processing parameters of electronic auxiliary materials, comprising:

[0006] Acquire electronic auxiliary materials to be processed, identify initial processing parameters corresponding to the electronic auxiliary materials to be processed, collect real-time operation data corresponding to preset processing equipment based on the initial processing parameters, classify the real-time operation data to obtain a classified data set, and extract a core parameter subset from the classified data set;

[0007] Generate a machining process curve corresponding to the core parameter subset, perform slope analysis on the machining process curve to obtain a slope change sequence, identify a mutation point in the slope change sequence, and calculate a mutation impact value corresponding to the mutation point;

[0008] Collecting the fluctuation characteristics corresponding to the mutation influence value, identifying the fluctuation range of the fluctuation characteristics at different processing stages, calculating the auxiliary material stability value corresponding to the electronic auxiliary material to be processed based on the fluctuation range, and determining the processing direction corresponding to the electronic auxiliary material to be processed based on the auxiliary material stability value;

[0009] Identify the processing adjustment strategy corresponding to the processing direction, monitor the effect data after the processing adjustment strategy is implemented in real time, compare the effect data with the preset target data, and obtain the effect comparison parameter;

[0010] Query the potential improvement factor in the effect comparison parameter, determine the improvement level corresponding to the potential improvement factor, set the improvement level index corresponding to the improvement level, and generate the optimization plan corresponding to the electronic auxiliary material to be processed based on the improvement level index.

[0011] Optionally, the collecting of real-time operation data corresponding to a preset processing device based on the initial processing parameters includes:

[0012] Based on the initial processing parameters, setting a preset time interval for data collection corresponding to the processing equipment;

[0013] Based on the time interval, collecting raw processing data corresponding to the preset processing equipment;

[0014] Standardizing the format of the original processed data to obtain a standard data set;

[0015] Analyze the operation phase corresponding to the data in the standard data set;

[0016] Based on the operation stage, real-time operation data corresponding to the preset processing equipment is collected.

[0017] Optionally, generating a machining process curve corresponding to the core parameter subset includes:

[0018] Extracting the time series corresponding to each parameter in the core parameter subset;

[0019] Performing interpolation processing on the time series to obtain a complete time series;

[0020] Based on the complete time series, drawing an initial curve sketch corresponding to the core parameter subset;

[0021] Smoothing the initial curve sketch to obtain a smoothed processing curve;

[0022] Marking key process nodes corresponding to the smoothing processing curve;

[0023] Based on the key process nodes, a machining process curve corresponding to the core parameter subset is generated.

[0024] Optionally, performing slope analysis on the machining process curve to obtain a slope change sequence includes:

[0025] Extracting discrete data points from the machining process curve;

[0026] Sorting the discrete data points to obtain an ordered data point set;

[0027] determining adjacent data points in the ordered set of data points;

[0028] Calculating the initial slope value between the adjacent data points;

[0029] Based on the initial slope value, a slope analysis is performed on the machining process curve to obtain a slope change sequence.

[0030] Optionally, calculating the mutation impact value corresponding to the mutation point includes:

[0031] The mutation impact value corresponding to the mutation point is calculated using the following formula:

[0032] ;

[0033] in, Indicates the mutation impact value corresponding to the mutation point, Represents the total number of influencing factors related to the mutation point, Indicates the quantitative index of influencing factors, Indicated in The influence degree value corresponding to each influencing factor is Indicated in The data weights corresponding to the influencing factors and the data related to the mutation point, Indicates the number of characteristic attributes corresponding to the mutation point, Indicates the number index of feature attributes, Indicates The characteristic quantization value corresponding to the characteristic attribute of each mutation point.

[0034] Optionally, the calculating, based on the fluctuation range, the auxiliary material stability value corresponding to the electronic auxiliary material to be processed includes:

[0035] The auxiliary material stability value corresponding to the electronic auxiliary material to be processed is calculated using the following formula:

[0036] ;

[0037] in, Indicates the auxiliary material stability value corresponding to the electronic auxiliary material to be processed, Indicates the total number of fluctuation factors in the fluctuation range. represents the quantitative index of the volatility factor, Indicated in The fluctuation amplitude value corresponding to each fluctuation factor is Indicated in The phase value corresponding to each fluctuation factor is Indicates the number of lower limit factors related to the lower limit of the fluctuation range, represents the quantitative index of the lower limit factor, Indicates The lower limit quantitative value corresponding to the lower limit factor is represents the number of upper limit factors related to the upper limit of the fluctuation range, represents the quantitative index of the upper limit factor, Indicates The upper limit quantitative value corresponding to the upper limit factor.

[0038] Optionally, determining the processing direction corresponding to the electronic auxiliary material to be processed based on the auxiliary material stability value includes:

[0039] Determine the numerical range corresponding to the stability value of the auxiliary material;

[0040] Based on the numerical range, dividing the graded stability zones corresponding to the stability values ​​of the auxiliary materials;

[0041] Analyzing the preliminary processing direction corresponding to the graded stable area;

[0042] Performing machining simulation on the preliminary machining direction to obtain machining simulation data;

[0043] Based on the processing simulation data, a processing direction corresponding to the electronic auxiliary material to be processed is determined.

[0044] Optionally, comparing the effect data with preset target data to obtain effect comparison parameters includes:

[0045] Identify the effect indicator item to which the effect data belongs;

[0046] Reclassify the effect indicator items according to the classification framework of the preset target data to obtain a classified effect subset;

[0047] Comparing the classification effect subset with the corresponding subset of preset target data to obtain a comparison difference;

[0048] Based on the comparison difference, the effect data is compared with the preset target data to obtain effect comparison parameters.

[0049] Optionally, the querying of the potential improvement factor in the effect comparison parameter includes:

[0050] Analyzing abnormal fluctuation labels in the effect comparison parameters;

[0051] Trace back the processing link corresponding to the abnormal fluctuation label;

[0052] Based on the processing links, searching for the root causes of problems in the historical processing data;

[0053] Extract the core problem factors corresponding to the root causes of the problems;

[0054] Based on the core problem factors, potential improvement factors in the effect comparison parameters are queried.

[0055] In order to solve the above problems, the present invention also provides an electronic auxiliary material processing parameter intelligent optimization system, the system comprising:

[0056] A subset extraction module is used to obtain electronic auxiliary materials to be processed, identify initial processing parameters corresponding to the electronic auxiliary materials to be processed, collect real-time operation data corresponding to preset processing equipment based on the initial processing parameters, classify the real-time operation data to obtain a classified data set, and extract a core parameter subset from the classified data set;

[0057] An influence value calculation module is used to generate a machining process curve corresponding to the core parameter subset, perform slope analysis on the machining process curve to obtain a slope change sequence, identify a mutation point in the slope change sequence, and calculate a mutation influence value corresponding to the mutation point;

[0058] A direction determination module, used for collecting the fluctuation characteristics corresponding to the mutation influence value, identifying the fluctuation range of the fluctuation characteristics at different processing stages, calculating the auxiliary material stability value corresponding to the electronic auxiliary material to be processed based on the fluctuation range, and determining the processing direction corresponding to the electronic auxiliary material to be processed based on the auxiliary material stability value;

[0059] An effect comparison module is used to identify the processing adjustment strategy corresponding to the processing direction, monitor the effect data after the processing adjustment strategy is implemented in real time, compare the effect data with the preset target data, and obtain effect comparison parameters;

[0060] The scheme generation module is used to query the potential improvement factor in the effect comparison parameter, determine the improvement level corresponding to the potential improvement factor, set the improvement level index corresponding to the improvement level, and generate the optimization scheme corresponding to the electronic auxiliary material to be processed based on the improvement level index.

[0061] Compared with the problems described in the background technology, the present invention obtains the electronic auxiliary materials to be processed and identifies the initial processing parameters corresponding to the electronic auxiliary materials to be processed, which helps to accurately grasp the production starting point, perform targeted processing according to the characteristics of different auxiliary materials, avoid blind operation, understand the processing requirements in advance, reasonably arrange production resources, and improve production efficiency. The present invention generates a processing process curve corresponding to the core parameter subset, which can intuitively present the dynamic changes of key parameters in the processing process, so that operators can clearly grasp the stability and trend of the processing process, such as the fluctuation of parameters such as temperature and pressure over time, which helps to timely discover processing abnormalities, and quickly locate the links where problems may occur through sudden changes in the curve, deviations from the normal range, etc., and take measures in advance to prevent the production of defective products and ensure product quality. Furthermore, the present invention collects the fluctuation characteristics corresponding to the sudden change influence value and identifies the fluctuation range of the fluctuation characteristics in different processing stages, which can help predict in advance the abnormalities that will occur in the processing process. Normal situation, it is helpful to accurately optimize the processing parameters. By understanding the fluctuation range of different stages, the parameters can be adjusted in a targeted manner to reduce the impact value of mutations, and ensure the high efficiency and stability of the production process. Further, the present invention identifies the processing adjustment strategy corresponding to the processing direction, and monitors the effect data after the implementation of the processing adjustment strategy in real time, which helps to timely discover the deviation in the processing process and make targeted adjustments, ensure the stability of processing quality, reduce the generation of defective products, and improve the product qualification rate. It can quickly verify the effectiveness of the adjustment strategy, accumulate experience data, provide reference for subsequent similar processing tasks, optimize the processing flow, and improve the overall production efficiency. Finally, the present invention can accurately locate the weak links in the processing flow by querying the potential improvement factors in the effect comparison parameters, and clearly identify whether there are problems in product quality, processing efficiency or cost control, which helps to predict risks in advance, avoid large-scale production delays or quality accidents caused by the accumulation of small problems, and effectively improve resource utilization efficiency. Therefore, the electronic auxiliary material processing parameter intelligent optimization method and system provided by the embodiment of the present invention can improve the production efficiency of electronic auxiliary materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A schematic diagram of a process flow of an intelligent optimization method for processing parameters of electronic auxiliary materials provided by an embodiment of the present invention;

[0063] Figure 2 A schematic diagram of modules for implementing the electronic auxiliary material processing parameter intelligent optimization system provided in one embodiment of the present invention.

[0064] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0065] 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.

[0066] The embodiment of the present application provides an intelligent optimization method for processing parameters of electronic auxiliary materials. The execution subject of the intelligent optimization method for processing parameters of electronic auxiliary materials includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the intelligent optimization method for processing parameters of electronic auxiliary materials can be executed by software or hardware installed in a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0067] Embodiment 1:

[0068] Reference Figure 1 FIG. 1 is a flow chart of an intelligent optimization method for processing parameters of electronic auxiliary materials provided by an embodiment of the present invention. In this embodiment, the intelligent optimization method for processing parameters of electronic auxiliary materials includes:

[0069] S1. Obtain electronic auxiliary materials to be processed, identify initial processing parameters corresponding to the electronic auxiliary materials to be processed, collect real-time operation data corresponding to preset processing equipment based on the initial processing parameters, classify the real-time operation data to obtain a classified data set, and extract a core parameter subset from the classified data set.

[0070] The present invention obtains the electronic auxiliary materials to be processed and identifies the initial processing parameters corresponding to the electronic auxiliary materials to be processed, which helps to accurately grasp the production starting point, perform targeted processing according to the characteristics of different auxiliary materials, avoid blind operation, understand the processing requirements in advance, reasonably arrange production resources, and improve production efficiency.

[0071] Among them, the electronic auxiliary materials to be processed refer to various auxiliary materials that are about to enter the processing flow and are used in the manufacturing process of electronic products, such as electronic paste, conductive tape, insulating sheet, etc.; the initial processing parameters refer to a series of basic data set when the electronic auxiliary materials are started to be processed, including but not limited to processing temperature, pressure, time, speed, etc. These parameters are usually determined based on past experience, material specifications or preliminary process designs, which determine the initial conditions and operating specifications of the processing process and are the starting basis for subsequent optimization and adjustment of the processing process. Different electronic auxiliary materials will correspond to different initial processing parameter combinations due to their materials, uses and other factors. Optionally, the identification of the initial processing parameters corresponding to the electronic auxiliary materials to be processed can be achieved through optimization algorithms, such as genetic algorithms, particle swarm optimization and other algorithms.

[0072] Furthermore, based on the initial processing parameters, the present invention collects real-time operating data corresponding to preset processing equipment, can monitor the processing process in real time, promptly discover deviations between the equipment operating status and the initial settings, and avoid product quality problems caused by equipment failure or performance fluctuations, thereby optimizing the entire production process and improving production efficiency and the processing quality of electronic auxiliary materials.

[0073] Among them, the real-time operation data refers to the latest data collected from the processing equipment again based on the characteristics of the operation stage. That is, when it is clear that the current stage is in a specific operation stage (such as the main processing stage), in order to more accurately grasp the subtle changes in the operation of the equipment in this stage, the temperature, pressure, speed and other data corresponding to the processing equipment at this moment are re-collected according to the previously set time interval.

[0074] As an embodiment of the present invention, the method of collecting real-time operation data corresponding to a preset processing equipment based on the initial processing parameters includes: setting a time interval for collecting data corresponding to the preset processing equipment based on the initial processing parameters; collecting original processing data corresponding to the preset processing equipment based on the time interval; standardizing the format of the original processing data to obtain a standard data set; analyzing the operation stage corresponding to the data in the standard data set; and collecting real-time operation data corresponding to the preset processing equipment based on the operation stage.

[0075] Among them, the time interval refers to the time span determined according to the initial processing parameters and used to regularly start collecting the preset processing equipment operation data. For example, if the initial processing parameters involve a temperature-sensitive processing technology and the heating process of the process needs to be precisely controlled, the time interval can be set to once every 3 seconds in order to capture the changes in the equipment operation status in time; the raw processing data refers to the unprocessed physical quantity values ​​directly captured by sensors installed at various key parts of the processing equipment (such as heating areas, pressure chambers, transmission components, etc.) at set time intervals, such as real-time temperature readings obtained by temperature sensors, pressure values ​​recorded by pressure sensors, and speed sensors. The equipment operating speed value fed back by the sensor, etc.; the standard data set refers to the product of a series of normalization processing on the original processing data. Specifically, the data cleaning algorithm is first used to remove data points with obvious errors or abnormalities, such as the maximum or minimum values ​​caused by temporary sensor failure; then the unit of the data, the number of significant digits retained and other formats are unified; the operation stage refers to the different time periods divided into the entire processing process according to the technological characteristics of the electronic auxiliary material processing flow. By analyzing the characteristics of the data in the standard data set, such as the changing trends of parameters such as temperature, pressure, and speed, it is determined which processing stage the current data corresponds to, which helps to understand the operating performance of the equipment in each key time period in a targeted manner.

[0076] Furthermore, the setting of the time interval for data collection corresponding to the preset processing equipment can be achieved through a dynamic adaptive algorithm, such as: Q-learning algorithm, taking the energy consumption of the processing equipment, product quality stability, etc. as reward signals, and initially randomly setting a time interval range (such as 5-15 seconds); the collection of the original processing data corresponding to the preset processing equipment can be achieved through sensor network technology, such as: deploying various sensors at key parts of the processing equipment to form a sensor network, so as to obtain the original processing data; the format standardization of the original processing data can be achieved through ETL tools, such as: Sqoop tool can automatically convert the pressure unit from psi to kPa and the time unit from milliseconds to seconds according to the conversion rules in the configuration file, efficiently achieve format standardization, and generate a standard data set; the analysis of the operation stage corresponding to the data in the standard data set can be achieved through a rule-based expert system, such as: after the standard data set is input into the expert system, the system performs reasoning and judgment according to these rules to obtain the operation stage; the collection of real-time operation data corresponding to the preset processing equipment can be achieved through data acquisition tools, such as: Modbus, OPC UA and other tools.

[0077] By extracting a subset of core parameters from the classified data set, the present invention helps to accurately grasp the core links in the processing process and clarify the changing trends and laws of key parameters, thereby providing a precise direction for optimizing the processing parameters and avoiding wasting resources and time on non-critical factors.

[0078] Among them, the core parameter subset refers to a set of parameters that have a key impact on the electronic auxiliary material processing process and the final product quality and can reflect the essential characteristics and core mechanisms of the processing, which are screened out from the classified data set (the data set contains various operating data of the preset processing equipment collected based on the initial processing parameters). These parameters usually cover important variables that are directly related to the changes in the physical and chemical properties of electronic auxiliary materials, such as key temperature nodes in the processing process, pressure extremes, key thresholds of equipment operating speed, sensitive ranges of material flow, etc. Optionally, the extraction of the core parameter subset in the classified data set can be achieved through machine learning algorithms, such as random forest, LASSO regression and other algorithms.

[0079] S2. Generate a machining process curve corresponding to the core parameter subset, perform slope analysis on the machining process curve to obtain a slope change sequence, identify a mutation point in the slope change sequence, and calculate a mutation impact value corresponding to the mutation point.

[0080] The present invention can intuitively present the dynamic changes of key parameters in the processing process by generating a processing process curve corresponding to the core parameter subset, so that the operator can clearly grasp the stability and trend of the processing process, such as the fluctuation of parameters such as temperature and pressure over time, which helps to timely discover processing abnormalities, and quickly locate the links where problems may occur through sudden changes in the curve, deviations from the normal range, etc., and take measures in advance to prevent the production of defective products and ensure product quality.

[0081] Among them, the processing process curve refers to the final curve formed by improving the smooth processing curve with key process nodes as important identifiers. It not only accurately shows the change pattern of core parameters over time, but also highlights the parameter status corresponding to the key nodes, and fully presents the dynamic changes of the core parameter subset in the entire processing process.

[0082] As an embodiment of the present invention, the generation of the processing process curve corresponding to the core parameter subset includes: extracting the time series corresponding to each parameter in the core parameter subset; interpolating the time series to obtain a complete time series; drawing an initial curve sketch corresponding to the core parameter subset based on the complete time series; smoothing the initial curve sketch to obtain a smooth processing curve; marking the key process nodes corresponding to the smooth processing curve; and generating the processing process curve corresponding to the core parameter subset based on the key process nodes.

[0083] Among them, the time series refers to a series of data values ​​formed by continuously recording each parameter in the core parameter subset in chronological order. For example, if the core parameter subset includes the temperature parameter in the processing of a certain electronic auxiliary material, then the temperature time series is the temperature values ​​collected at specific time intervals (such as every 5 seconds) during the entire processing period, which are arranged in sequence, and it directly reflects the dynamic change trajectory of the parameter over time; the complete time series refers to a sequence with more continuous and complete data points obtained through interpolation processing on the basis of the original time series. It uses interpolation algorithms, such as linear interpolation, spline interpolation, etc., according to the trend of existing data points, to reasonably infer and supplement missing values, so that the time series has no interruption on the time axis, ensuring that the overall picture of parameter changes can be accurately presented; the initial curve sketch refers to a preliminary curve shape that is simply outlined based on the complete time series using drawing tools or programming functions (such as Python's matplotlib library function) with time as the horizontal axis and the core parameter as the vertical axis; the smoothed processing curve refers to the product after smoothing the initial curve sketch. Because the initial sketch may be affected by data collection noise, short-term fluctuations in equipment, etc., the curve may be jagged or have abnormal jitter. Smoothing techniques such as moving average method and Gaussian filtering are used to eliminate these irregular fluctuations and make the curve more truly reflect the stable change law of core parameters. The key process nodes refer to the parameter positions corresponding to specific moments or stages in the electronic auxiliary material processing flow that are of symbolic significance and play a key role in the processing quality and progress, such as the starting point when the electronic auxiliary material begins to heat up, the moment when the material is officially put into the processing equipment, the moment when the critical chemical reaction temperature is reached, etc. These nodes are marked on the smooth processing curve.

[0084] Furthermore, the extraction of the time series corresponding to each parameter in the core parameter subset can be achieved through a sequence acquisition tool, such as Python, MATLAB and other tools; the interpolation processing of the time series can be achieved through an interpolation algorithm, such as linear interpolation, spline interpolation and other algorithms; the drawing of the initial curve sketch corresponding to the core parameter subset can be achieved through a sketch drawing tool, such as Seaborn, Plotly and other tools; the smoothing of the initial curve sketch can be achieved through a smoothing algorithm, such as moving average method, Gaussian filtering and other algorithms; the marking of the key process nodes corresponding to the smoothed processing curve can be achieved through a key node identification method, such as peak detection, threshold detection and other methods; the generation of the processing process curve corresponding to the core parameter subset can be achieved through a curve generation method, such as neural network fitting, segmented fitting and other methods.

[0085] The present invention performs slope analysis on the processing process curve to obtain a slope change sequence, which helps to accurately grasp the dynamic characteristics of the processing process. For example, a sudden increase or decrease in the slope may indicate equipment failure, raw material abnormality or process instability, thereby achieving early warning and avoiding the production of defective products.

[0086] Among them, the slope change sequence refers to a sequence that is formed by arranging and integrating the initial slope values ​​corresponding to different intervals of the machining process curve in order based on time. It fully presents the changing rate of the core parameters in the entire machining process. By observing the ups and downs, mutations and other characteristics in the slope change sequence, we can gain insight into whether the machining process is stable and whether there are abnormal acceleration or deceleration links, thereby providing key information for optimizing machining parameters and diagnosing equipment failures.

[0087] As an embodiment of the present invention, the slope analysis of the processing process curve to obtain a slope change sequence includes: extracting discrete data points in the processing process curve; sorting the discrete data points to obtain an ordered data point set; determining adjacent data points in the ordered data point set; calculating the initial slope value between the adjacent data points; and based on the initial slope value, performing slope analysis on the processing process curve to obtain a slope change sequence.

[0088] The discrete data points refer to the isolated and scattered data coordinates directly extracted from the generated machining process curve. These coordinates are composed of the horizontal axis value representing the machining time and the vertical axis value of the core parameters (such as temperature, pressure, speed, etc.) at the corresponding time, which are the basic constituent elements of the curve; the ordered data point set refers to the set obtained by arranging and sorting the extracted discrete data points in the order of machining time. For example, if the discrete data points are initially extracted in disorder, they are arranged in ascending order from the data points at the start of machining by comparing the timestamps or data acquisition serial numbers; the adjacent data points refer to the two data points in the ordered data point set that are adjacent to each other, which reflect the changes in the core parameters in a very short continuous time interval and are the basic units for calculating the slope. The connecting line between adjacent data points is approximately the tangent of the machining process curve in this small interval; the initial slope value refers to the slope value calculated for each pair of adjacent data points, which is the initial slope value.

[0089] Furthermore, the extraction of discrete data points in the processing process curve can be achieved through time series analysis tools, such as: using resample() of the pandas library in Python to extract periodic discrete data points from continuous data; the sorting of the discrete data points can be achieved through a sorting algorithm, such as: bubble sort, selection sort and other algorithms; the determination of adjacent data points in the ordered data point set can be achieved through a data window method, such as: sliding window, weighted sliding window and other methods; the calculation of the initial slope value between adjacent data points can be achieved through a slope algorithm, such as: difference method, differential method calculation and other algorithms; the slope analysis of the processing process curve can be achieved through a sliding average method, such as: simple sliding average, weighted sliding average and other methods.

[0090] The present invention can accurately indicate abnormal situations that may occur in the processing process by identifying the mutation points in the slope change sequence, and through in-depth analysis of the mutation points, it is helpful to quickly locate the root cause of the instability of the processing process, provide a clear direction for accurately adjusting the processing parameters and optimizing the process conditions, and improve the production efficiency and the stability of product quality.

[0091] Among them, the mutation point refers to the point in the slope change sequence where the slope value changes significantly, suddenly and deviates from the normal change trend. In the process of electronic auxiliary material processing, it may be due to a sudden equipment failure that causes an instantaneous imbalance of processing parameters, such as a sudden rise in temperature or a sharp drop in pressure, which is reflected in the sudden change in the slope; it may also be due to differences in raw material batches that cause a sudden change in its reaction characteristics at a certain processing stage, thereby causing a large fluctuation in the change rate of core parameters. These abnormal points highlighted in the slope change sequence are mutation points. Optionally, the identification of mutation points in the slope change sequence can be achieved through a threshold-based judgment method, such as: setting a threshold range for slope change, and when the slope value of a point in the slope change sequence exceeds this threshold range, it is judged as a mutation point.

[0092] Furthermore, the present invention can accurately quantify the degree of interference of the mutation point on the stability of the entire processing process and product quality by calculating the mutation impact value corresponding to the mutation point, and can deeply trace the root causes of the factors that cause the mutation, such as the specific location of the equipment failure, the abnormal fluctuation range of the raw material characteristics, etc., to provide a strong basis for accurate repair and adjustment.

[0093] The mutation impact value refers to a comprehensive indicator used to measure the impact of a mutation point in a specific situation. It reflects the degree of interference of the mutation point on the overall process or system in a numerical form by considering multiple factors related to the mutation point and their interrelationships.

[0094] As an embodiment of the present invention, the calculating the mutation impact value corresponding to the mutation point includes:

[0095] The mutation impact value corresponding to the mutation point is calculated using the following formula:

[0096] ;

[0097] in, Indicates the mutation impact value corresponding to the mutation point, Represents the total number of influencing factors related to the mutation point, Indicates the quantitative index of influencing factors, Indicated in The influence degree value corresponding to each influencing factor is Indicated in The data weights corresponding to the influencing factors and the data related to the mutation point, Indicates the number of characteristic attributes corresponding to the mutation point, Indicates the number index of feature attributes, Indicates The characteristic quantization value corresponding to the characteristic attribute of each mutation point.

[0098] In detail, the influencing factors refer to various conditions, variables or events that can cause the generation of mutation points or are closely related to the appearance of mutation points. For example, in the production process of electronic components, temperature, humidity, raw material purity, equipment operation status, etc. can all be influencing factors; the influence degree value refers to the quantification of the role played by each influencing factor in the process of causing the appearance of mutation points, which reflects the specific contribution of a single influencing factor to the generation of mutation points. The larger the value, the greater the influence of the factor on the generation of mutation points; the data weight refers to the importance of each influencing factor and the data related to the mutation point. Different influencing factors have different weights on the mutation point. The data weight is used to reflect this difference in importance. The larger the weight, the more important the influence of the factor on the mutation point; the characteristic quantization value refers to the value obtained after quantifying various characteristic attributes of the mutation point itself. These characteristic attributes can be the physical, chemical, geometric and other aspects of the mutation point.

[0099] S3. Collect the fluctuation characteristics corresponding to the mutation influence value, identify the fluctuation range of the fluctuation characteristics in different processing stages, calculate the auxiliary material stability value corresponding to the electronic auxiliary material to be processed based on the fluctuation range, and determine the processing direction corresponding to the electronic auxiliary material to be processed based on the auxiliary material stability value.

[0100] The present invention collects the fluctuation characteristics corresponding to the mutation influence value and identifies the fluctuation range of the fluctuation characteristics in different processing stages, which can help predict abnormal situations that may occur in the processing process in advance and help to accurately optimize the processing parameters. By understanding the fluctuation range of different stages, the parameters can be adjusted in a targeted manner to reduce the mutation influence value and ensure the efficiency and stability of the production process.

[0101] Among them, the fluctuation characteristics refer to the changing rules and characteristics of the mutation influence value over time or the progress of the processing process, which include the change frequency, change amplitude, change trend (such as increase, decrease or periodic change) of the mutation influence value. For example, in the processing of electronic auxiliary materials, the mutation influence value may fluctuate frequently and slightly in certain time periods, while in other time periods, a large one-time mutation may occur. These are all manifestations of the fluctuation characteristics; the fluctuation range refers to the interval defined by the upper and lower limits of the fluctuation of the mutation influence value in a specific processing stage. For example, in the initial stage of electronic auxiliary material processing, the fluctuation range of the mutation influence value can be determined as [0.1, 0.5], which means that in this stage, the mutation influence value usually fluctuates in the range of 0.1 to 0.5. Exceeding this range may indicate that an abnormal situation has occurred in the processing process. Optionally, the acquisition of the fluctuation characteristics corresponding to the mutation influence value can be achieved by Fourier transform, such as converting the time domain signal into the frequency domain signal, and determining the fluctuation characteristics by analyzing the spectrum in the frequency domain; the identification of the fluctuation range of the fluctuation characteristics in different processing stages can be achieved by statistical analysis tools, such as SPSS and other tools.

[0102] Furthermore, the present invention calculates the auxiliary material stability value corresponding to the electronic auxiliary material to be processed based on the fluctuation range, which can intuitively quantify the stability degree of the electronic auxiliary material during the processing, provide an accurate numerical basis for evaluating the processing quality, and facilitate rapid judgment of whether the processing process is in a stable and controllable state.

[0103] Among them, the auxiliary material stability value refers to a value calculated by the following formula, which is used to quantify the stability of the electronic auxiliary materials to be processed during the processing process. This value comprehensively considers various factors within the fluctuation range.

[0104] As an embodiment of the present invention, the calculating, based on the fluctuation range, the auxiliary material stability value corresponding to the electronic auxiliary material to be processed includes:

[0105] The auxiliary material stability value corresponding to the electronic auxiliary material to be processed is calculated using the following formula:

[0106] ;

[0107] in, Indicates the auxiliary material stability value corresponding to the electronic auxiliary material to be processed, Indicates the total number of fluctuation factors in the fluctuation range. represents the quantitative index of the volatility factor, Indicated in The fluctuation amplitude value corresponding to each fluctuation factor is Indicated in The phase value corresponding to each fluctuation factor is Indicates the number of lower limit factors related to the lower limit of the fluctuation range, represents the quantitative index of the lower limit factor, Indicates The lower limit quantitative value corresponding to the lower limit factor is represents the number of upper limit factors related to the upper limit of the fluctuation range, represents the quantitative index of the upper limit factor, Indicates The upper limit quantitative value corresponding to the upper limit factor.

[0108] In detail, the fluctuation factor refers to the sum of various related factors that can cause changes in the stability of the auxiliary materials within the fluctuation range. These factors can be variables in the processing process, such as fluctuations in temperature, pressure, humidity, etc.; the fluctuation amplitude value refers to the quantitative value of the change amplitude of each fluctuation factor during the fluctuation process. For each fluctuation factor, there is a corresponding fluctuation amplitude value, which is used to indicate the magnitude of the change of the factor during the fluctuation; the phase value refers to the quantitative value of the phase of each fluctuation factor during the fluctuation process, which reflects the relative position of the fluctuation factor in time or space, and is used to describe the synchronization or difference of the fluctuation; the lower limit factor refers to various factors related to the lower limit of the fluctuation range. These The factors determine the lower limit value of the fluctuation range. For example, in the processing process, the minimum value of certain parameters can be determined by lower limit factors such as equipment performance and process requirements; the lower limit quantitative value refers to the quantitative representation corresponding to each lower limit factor. These values ​​are used to determine the lower limit of the fluctuation range and are the specific manifestation of the lower limit factors in mathematical calculations; the upper limit factors are various factors related to the upper limit of the fluctuation range. These factors determine the upper limit value of the fluctuation range. For example, in the processing process, the maximum value of certain parameters can be determined by upper limit factors such as safety limits and material properties; the upper limit quantitative value refers to the quantitative representation corresponding to each upper limit factor. These values ​​are used to determine the upper limit of the fluctuation range and are the specific manifestation of the upper limit factors.

[0109] Furthermore, the present invention determines the processing direction corresponding to the electronic auxiliary material to be processed based on the auxiliary material stability value, which can ensure the accuracy of the processing process. Selecting a suitable processing direction through the auxiliary material stability value can avoid material waste and defective products caused by blind processing, and can ensure the consistency of product quality. Selecting a suitable processing direction under the same auxiliary material stability value can make product performance more stable and reliable, and improve the overall quality level of the product.

[0110] Among them, the processing direction refers to the specific direction of processing the electronic auxiliary materials to be processed, which is determined after simulating the preliminary processing direction and analyzing the processing simulation data. This processing direction is the most suitable processing path and method for the electronic auxiliary materials to be processed after comprehensively considering the auxiliary material stability value, graded stability zone and processing simulation results.

[0111] As an embodiment of the present invention, determining the processing direction corresponding to the electronic auxiliary material to be processed based on the auxiliary material stability value includes: determining the numerical range corresponding to the auxiliary material stability value; dividing the graded stability zone corresponding to the auxiliary material stability value based on the numerical range; analyzing the preliminary processing direction corresponding to the graded stability zone; performing processing simulation on the preliminary processing direction to obtain processing simulation data; and determining the processing direction corresponding to the electronic auxiliary material to be processed based on the processing simulation data.

[0112] Among them, the numerical range refers to an interval in which the auxiliary material stability value is located. For example, the auxiliary material stability value can be between 0 and 100. According to different production experience and process requirements, this interval can be further subdivided into multiple sub-intervals, such as 0-20, 20-50, 50-100, etc., and each sub-interval is a numerical range; the graded stability zone refers to different areas divided according to the numerical range of the auxiliary material stability value. For example, the auxiliary material stability value in the interval of 0-20 corresponds to the graded stability zone with low stability, and 50-100 corresponds to the graded stability zone with high stability; the preliminary processing direction refers to the approximate processing direction determined for each graded stability zone. For example, for the graded stability zone with low stability, the preliminary processing direction can be a more conservative and precise processing method; for the graded stability zone with high stability, the preliminary processing direction can be an efficient and fast processing method; the processing simulation data refers to the data obtained after the preliminary processing direction is processed and simulated, and these data include but are not limited to parameter changes (such as temperature, pressure, processing speed, etc.) during the processing, product quality indicators (such as dimensional accuracy, surface roughness, performance parameters, etc.), processing time, etc.

[0113] Furthermore, the determination of the numerical range corresponding to the auxiliary material stability value can be achieved through a statistical analysis method, such as: by collecting a large amount of historical data and current data, using statistical methods (such as mean, standard deviation) to determine a reasonable numerical range; the division of the graded stability zone corresponding to the auxiliary material stability value can be achieved through a decision tree model, such as: taking the auxiliary material stability value as an input variable, outputting the graded stability zone, and automatically dividing the stability zone; the analysis of the preliminary processing direction corresponding to the graded stability zone can be achieved through a heuristic algorithm, such as: genetic algorithm, simulated annealing, etc.; the processing simulation of the preliminary processing direction can be achieved through a processing simulation tool, such as: FEA tool simulates the temperature change, stress distribution, etc. under the preliminary processing direction to obtain processing simulation data; the determination of the processing direction corresponding to the electronic auxiliary material to be processed can be achieved through a multi-objective optimization algorithm, such as: NSGA-II and other algorithms.

[0114] S4. Identify the processing adjustment strategy corresponding to the processing direction, monitor the effect data after the processing adjustment strategy is implemented in real time, compare the effect data with the preset target data, and obtain effect comparison parameters.

[0115] The present invention identifies the processing adjustment strategy corresponding to the processing direction and monitors the effect data after the implementation of the processing adjustment strategy in real time, which helps to promptly discover deviations in the processing process and make targeted adjustments, thereby ensuring stable processing quality, reducing the generation of defective products, and improving product qualification rate. It can quickly verify the effectiveness of the adjustment strategy, accumulate experience data, provide reference for subsequent similar processing tasks, optimize the processing process, and improve overall production efficiency.

[0116] Among them, the processing adjustment strategy refers to a series of specific measures and methods taken according to the determined processing direction to optimize the processing process, improve product quality or deal with problems encountered in the processing process. For example, in the processing of electronic auxiliary materials, if the processing direction is to improve production efficiency, the processing adjustment strategy may include increasing the equipment running speed, optimizing the tool path, adjusting the amount of raw materials put in, etc.; if it is to improve product accuracy, the strategy may involve more precise processing parameter settings, increasing the frequency of inspections and using higher-precision processing equipment, etc.; the effect data refers to the relevant data reflecting the changes in the processing process and product quality obtained through various detection methods and data collection methods after the implementation of the processing adjustment strategy. These data may include the product Specific values ​​of dimensional accuracy, surface roughness, physical performance parameters (such as resistance and capacitance of electronic auxiliary materials), processing time, scrap rate, equipment energy consumption, etc. For example, if after implementing a processing adjustment strategy to improve production efficiency, it is monitored that the processing time is shortened by 20%, the scrap rate has not increased significantly, and the key performance parameters of the product are still within the qualified range, these data indicate that the strategy has achieved certain results in improving efficiency. Optionally, the identification of the processing adjustment strategy corresponding to the processing direction can be achieved through a strategy identification method, such as case reasoning method, decision tree method, etc.; the real-time monitoring of the effect data after the implementation of the processing adjustment strategy can be achieved through an effect monitoring method, such as comparative analysis method, trend analysis method.

[0117] Furthermore, the present invention obtains effect comparison parameters by comparing the effect data with preset target data, which can accurately quantify the actual effectiveness of the processing adjustment strategy and clearly show the gap with the expected target. By comparing the parameters, the effectiveness of the strategy can be quickly judged, and the strategy can be adjusted or optimized in time to avoid wasting resources on ineffective processing methods and improve resource utilization.

[0118] Among them, the preset target data refers to the ideal data value or range set before the processing of electronic auxiliary materials, based on the product's quality specifications, performance indicators, production efficiency expectations and successful experience of similar processing in the past. It covers quantitative indicators such as dimensional accuracy, physical performance parameters, appearance quality standards, processing time, cost control and other aspects; the effect comparison parameter refers to a set of parameters used to comprehensively and systematically reflect the achievement of the effect data compared to the preset target data after comprehensively considering all comparison differences. It may include the comparison difference of each indicator, the mean value of the difference, the variance and other statistics, or the comprehensive difference weighted by importance.

[0119] As an embodiment of the present invention, the effect data is compared with the preset target data to obtain effect comparison parameters, including: identifying the effect indicator item to which the effect data belongs; reclassifying the effect indicator item according to the classification structure of the preset target data to obtain a classified effect subset; numerically comparing the classified effect subset with the corresponding subset of the preset target data to obtain a comparison difference; based on the comparison difference, comparing the effect data with the preset target data to obtain effect comparison parameters.

[0120] Among them, the effect index item refers to a single data index or data category that can reflect the effectiveness of a specific aspect of the processing adjustment strategy after the implementation of the collected effect data. For example, in the processing of electronic auxiliary materials, the effect data covers the product's dimensional accuracy, surface roughness, processing time and other information; the classified effect subset refers to a set formed by regrouping and integrating the identified effect index items according to the classification framework pre-set by the preset target data. For example, the preset target data is divided into three categories according to product quality, processing efficiency, and cost control. Then all the effect index items related to product quality extracted from the effect data (such as dimensional accuracy, surface flatness, impurity content, etc.) are classified into a classified effect subset; the comparison difference refers to the difference obtained by subtracting the numerical value of the same index item in the classified effect subset from the corresponding subset of the preset target data. Taking processing efficiency as an example, the expected single-batch processing time of the preset target data is 5 hours, while the actual single-batch processing time monitored in the classified effect subset is 6 hours. The difference of 1 hour between the two is the comparison difference, which clearly quantifies the degree of deviation between the actual effect and the preset target on this indicator.

[0121] Furthermore, the identification of the effect indicator item to which the effect data belongs can be achieved through metadata analysis, such as: determining to which specific effect indicator each data point belongs by analyzing the metadata of the data; the reclassification of the effect indicator items can be achieved through cluster analysis, such as: grouping the effect indicator items based on similarity measurement to form a classified effect subset; the numerical comparison of the classified effect subset with the corresponding subset of the preset target data can be achieved through a vector difference algorithm, such as: expressing the classified effect subset and the corresponding subset of the preset target data in vector form, and obtaining a difference vector through vector subtraction operation, wherein each element in the vector is a comparison difference; the comparison of the effect data with the preset target data can be achieved through a comparison method, such as: absolute difference, relative difference and other comparison methods.

[0122] S5. Query the potential improvement factor in the effect comparison parameter, determine the improvement level corresponding to the potential improvement factor, set the improvement level index corresponding to the improvement level, and generate the optimization plan corresponding to the electronic auxiliary material to be processed based on the improvement level index.

[0123] By querying the potential improvement factors in the effect comparison parameters, the present invention can accurately locate the weak links in the processing flow, clarify whether there are problems in product quality, processing efficiency or cost control, etc., help to predict risks in advance, avoid large-scale production delays or quality accidents due to the accumulation of small problems, and effectively improve resource utilization efficiency.

[0124] Among them, the potential improvement factors refer to those key variables or factors found in the effect comparison parameters based on the analysis and identification of core problem factors, which can be improved and optimized to eliminate or reduce abnormal fluctuations and enhance effects. For example, if it is found that the equipment maintenance cycle is a potential improvement factor affecting product quality, then the product quality can be improved by shortening the equipment maintenance cycle, optimizing the maintenance process and other measures.

[0125] As an embodiment of the present invention, the querying of potential improvement factors in the effect comparison parameters includes: analyzing abnormal fluctuation labels in the effect comparison parameters; tracing back the processing links corresponding to the abnormal fluctuation labels; based on the processing links, retrieving the root causes of the problems in historical processing data; extracting the core problem factors corresponding to the root causes of the problems; and based on the core problem factors, querying the potential improvement factors in the effect comparison parameters.

[0126] Among them, the abnormal fluctuation label refers to a specific symbol, name or classification used to identify abnormal fluctuations in data in the effect comparison parameters. For example, in product quality control, if the value of a quality indicator suddenly exceeds the normal fluctuation range, this abnormal situation can be given a specific label, such as "abnormal quality fluctuation-excessive dimensional deviation"; the processing link refers to the specific stages and operation steps directly related to product manufacturing, service provision or task execution in the entire production or business process, which covers the entire process from raw material input to final product or service output, including but not limited to production and processing, assembly, inspection, packaging and other links, each of which can have an impact on the final effect; the root cause of the problem refers to the cause of the problem. The root cause of abnormal fluctuations or problems in the processing link may involve many aspects such as human operating errors, equipment failures, unqualified raw material quality, unreasonable process design, and environmental factors. For example, the defective rate of a certain product suddenly increased. After investigation, it was found that the tool of a key equipment was seriously worn, resulting in a decrease in processing accuracy. Then tool wear is the root cause of this quality problem; the core problem factors refer to the most critical and influential factors extracted from the root cause of the problem. For example, in the case where the tool wear leads to an increase in the defective rate of the product, the speed of tool wear, the material of the tool, and the maintenance cycle of the equipment may be the key factors affecting tool wear. These key factors are the core problem factors.

[0127] Furthermore, the analysis of abnormal fluctuation labels in the effect comparison parameters can be achieved through an isolation forest algorithm, such as: using the isolation forest algorithm to perform anomaly detection, and automatically adding "abnormal fluctuation labels" to the effect comparison parameters that exceed the normal range; tracing the processing links corresponding to the abnormal fluctuation labels can be achieved through event log analysis methods, such as: analyzing event records in the production process to determine the processing links where abnormal fluctuations occur; retrieving the root causes of problems in historical processing data can be achieved through cause analysis tools, such as: fishbone diagrams, 5Whys and other tools; extracting the core problem factors corresponding to the root causes of the problems can be achieved through root cause analysis tools, such as: fishbone diagrams, 5Whys and other tools; querying the potential improvement factors in the effect comparison parameters can be achieved through factor query tools, such as: WEKA, SPSS and other tools.

[0128] The present invention provides clear guidance for the formulation of improvement measures by determining the improvement level corresponding to the potential improvement factor and setting the improvement level index corresponding to the improvement level. Different levels are matched with strategies of different strengths and complexities to improve the accuracy of optimization. Through clear level indicators, it is convenient to intuitively quantify the improvement results, continuously track and evaluate to ensure that the improvement direction does not deviate, thereby helping to improve the quality of electronic auxiliary material processing.

[0129] Among them, the improvement level refers to the classification and ranking of potential improvement factors based on factors such as the severity of their impact on the overall production or business process, the urgency of improvement, and the potential benefits that can be brought. For example, in the processing of electronic auxiliary materials, if a potential improvement factor is directly related to the core quality indicators of the product, once a deviation occurs, it will lead to a large amount of waste, seriously affecting delivery and reputation, then it belongs to a high level or key improvement level; if a factor only has a slight improvement effect on production efficiency and has little impact on other aspects, it can be at a low level or secondary improvement level; the improvement level indicator refers to the specific quantitative standard or qualitative description used to measure the achievement of each improvement level. Taking high-level improvement as an example, the indicator can include the improvement of key quality parameters of the product, such as dimensional accuracy must be controlled within ± Within 0.05mm, the product qualification rate must be increased from the current 80% to more than 95%; or the production efficiency can be significantly improved, such as a 30% increase in output per unit time and other quantitative goals. For medium-level improvements, the indicators are relatively mild, such as a 10% reduction in the time of a certain link in the processing flow, a 5% reduction in cost, etc. Optionally, the improvement level corresponding to the potential improvement factor can be determined through a project management tool, such as: automatically setting high priority (high level) for potential improvement factors affecting product delivery on the critical path, and setting low priority (low level) for non-critical factors with low resource investment and short construction period, so as to determine the improvement level; the improvement level indicator corresponding to the improvement level can be set through an indicator setting tool, such as: Wrike, Targetprocess and other tools.

[0130] Furthermore, the present invention generates an optimization plan corresponding to the electronic auxiliary materials to be processed based on the improvement level index, which can ensure that the improvement direction is accurate and correct, and tailor-make strategies according to the requirements of different level indicators, thereby fully considering the characteristics of electronic auxiliary materials processing, so that goals such as improving product quality, optimizing processing efficiency, and controlling costs can be quantified.

[0131] Among them, the optimization plan refers to a set of action strategies systematically planned for the electronic auxiliary materials to be processed based on the determined improvement level indicators, which covers the fine adjustment of the processing technology, such as precise control of parameters such as temperature, pressure, time, etc., to improve product quality and production efficiency; includes the upgrading and transformation or reasonable deployment of equipment to ensure its stable performance and adapt to higher-demand processing tasks; involves the optimization of raw material supply management, from screening high-quality suppliers to controlling the inspection of raw materials entering the site to ensure source quality; also includes the strengthening of personnel training and performance management, so as to encourage employees to master new processes and new technologies, improve operational proficiency and sense of responsibility, so as to achieve improvement goals in an all-round and step-by-step manner. Optionally, what methods, tools or algorithms can be used to generate the optimization plan corresponding to the electronic auxiliary materials to be processed, such as: JIRA, ProcessMaker and other tools.

[0132] Compared with the problems described in the background technology, the present invention obtains the electronic auxiliary materials to be processed and identifies the initial processing parameters corresponding to the electronic auxiliary materials to be processed, which helps to accurately grasp the production starting point, perform targeted processing according to the characteristics of different auxiliary materials, avoid blind operation, understand the processing requirements in advance, reasonably arrange production resources, and improve production efficiency. The present invention generates a processing process curve corresponding to the core parameter subset, which can intuitively present the dynamic changes of key parameters in the processing process, so that operators can clearly grasp the stability and trend of the processing process, such as the fluctuation of parameters such as temperature and pressure over time, which helps to timely discover processing abnormalities, and quickly locate the links where problems may occur through sudden changes in the curve, deviations from the normal range, etc., and take measures in advance to prevent the production of defective products and ensure product quality. Furthermore, the present invention collects the fluctuation characteristics corresponding to the sudden change influence value and identifies the fluctuation range of the fluctuation characteristics in different processing stages, which can help predict in advance the abnormalities that will occur in the processing process. Normal situation, it is helpful to accurately optimize the processing parameters. By understanding the fluctuation range of different stages, the parameters can be adjusted in a targeted manner to reduce the impact value of mutations, and ensure the high efficiency and stability of the production process. Further, the present invention identifies the processing adjustment strategy corresponding to the processing direction, and monitors the effect data after the implementation of the processing adjustment strategy in real time, which helps to timely discover the deviation in the processing process and make targeted adjustments, ensure the stability of processing quality, reduce the generation of defective products, and improve the product qualification rate. It can quickly verify the effectiveness of the adjustment strategy, accumulate experience data, provide reference for subsequent similar processing tasks, optimize the processing flow, and improve the overall production efficiency. Finally, the present invention can accurately locate the weak links in the processing flow by querying the potential improvement factors in the effect comparison parameters, and clearly identify whether there are problems in product quality, processing efficiency or cost control, which helps to predict risks in advance, avoid large-scale production delays or quality accidents caused by the accumulation of small problems, and effectively improve resource utilization efficiency. Therefore, the electronic auxiliary material processing parameter intelligent optimization method and system provided by the embodiment of the present invention can improve the production efficiency of electronic auxiliary materials.

[0133] Embodiment 2:

[0134] like Figure 2 The figure shows a functional module diagram of an intelligent optimization system for processing parameters of electronic auxiliary materials according to the present invention.

[0135] The electronic auxiliary material processing parameter intelligent optimization system 200 of the present invention can be installed in an electronic device. According to the functions to be implemented, the electronic auxiliary material processing parameter intelligent optimization system can include a subset extraction module 201, an influence value calculation module 202, a direction determination module 203, an effect comparison module 204 and a solution generation module 205. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0136] In the embodiment of the present invention, the functions of each module / unit are as follows:

[0137] The subset extraction module 201 is used to obtain the electronic auxiliary materials to be processed, identify the initial processing parameters corresponding to the electronic auxiliary materials to be processed, collect the real-time operation data corresponding to the preset processing equipment based on the initial processing parameters, classify the real-time operation data to obtain the classified data set, and extract the core parameter subset in the classified data set;

[0138] The impact value calculation module 202 is used to generate a machining process curve corresponding to the core parameter subset, perform slope analysis on the machining process curve to obtain a slope change sequence, identify a mutation point in the slope change sequence, and calculate a mutation impact value corresponding to the mutation point;

[0139] The direction determination module 203 is used to collect the fluctuation characteristics corresponding to the mutation influence value, identify the fluctuation range of the fluctuation characteristics at different processing stages, calculate the auxiliary material stability value corresponding to the electronic auxiliary material to be processed based on the fluctuation range, and determine the processing direction corresponding to the electronic auxiliary material to be processed based on the auxiliary material stability value;

[0140] The effect comparison module 204 is used to identify the processing adjustment strategy corresponding to the processing direction, monitor the effect data after the processing adjustment strategy is implemented in real time, compare the effect data with the preset target data, and obtain the effect comparison parameter;

[0141] The solution generation module 205 is used to query the potential improvement factor in the effect comparison parameter, determine the improvement level corresponding to the potential improvement factor, set the improvement level index corresponding to the improvement level, and generate the optimization solution corresponding to the electronic auxiliary material to be processed based on the improvement level index.

[0142] In detail, the modules in the electronic auxiliary material processing parameter intelligent optimization system 200 in the embodiment of the present invention are used in the same manner as described above. Figure 1 The same technical means are used as the intelligent optimization method for processing parameters of electronic auxiliary materials described in the text, and can produce the same technical effects, so they will not be repeated here.

[0143] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. An intelligent optimization method for processing parameters of electronic auxiliary materials, characterized in that: The method comprises: Acquire electronic auxiliary materials to be processed, identify initial processing parameters corresponding to the electronic auxiliary materials to be processed, collect real-time operation data corresponding to preset processing equipment based on the initial processing parameters, classify the real-time operation data to obtain a classified data set, and extract a core parameter subset from the classified data set; Generate a machining process curve corresponding to the core parameter subset, perform slope analysis on the machining process curve to obtain a slope change sequence, identify a mutation point in the slope change sequence, and calculate a mutation impact value corresponding to the mutation point, wherein calculating the mutation impact value corresponding to the mutation point includes: The mutation impact value corresponding to the mutation point is calculated using the following formula: ； in, Indicates the mutation impact value corresponding to the mutation point, Represents the total number of influencing factors related to the mutation point, Indicates the quantitative index of influencing factors, Indicated in The influence degree value corresponding to each influencing factor is Indicated in The data weights corresponding to the influencing factors and the data related to the mutation point, Indicates the number of characteristic attributes corresponding to the mutation point, Indicates the number index of feature attributes, Indicates The characteristic quantization value corresponding to the characteristic attribute of each mutation point; Collecting the fluctuation characteristics corresponding to the mutation impact value, identifying the fluctuation range of the fluctuation characteristics at different processing stages, and calculating the auxiliary material stability value corresponding to the electronic auxiliary material to be processed based on the fluctuation range, wherein the calculation of the auxiliary material stability value corresponding to the electronic auxiliary material to be processed based on the fluctuation range includes: The auxiliary material stability value corresponding to the electronic auxiliary material to be processed is calculated using the following formula: ； in, Indicates the auxiliary material stability value corresponding to the electronic auxiliary material to be processed, Indicates the total number of fluctuation factors in the fluctuation range. represents the quantitative index of the volatility factor, Indicated in The fluctuation amplitude value corresponding to each fluctuation factor is Indicated in The phase value corresponding to each fluctuation factor is Indicates the number of lower limit factors related to the lower limit of the fluctuation range, represents the quantitative index of the lower limit factor, Indicates The lower limit quantitative value corresponding to the lower limit factor is represents the number of upper limit factors related to the upper limit of the fluctuation range, represents the quantitative index of the upper limit factor, Indicates The upper limit quantization value corresponding to the upper limit factor is used to determine the processing direction corresponding to the electronic auxiliary material to be processed based on the auxiliary material stability value; Identify the processing adjustment strategy corresponding to the processing direction, monitor the effect data after the processing adjustment strategy is implemented in real time, compare the effect data with the preset target data, and obtain the effect comparison parameter; Query the potential improvement factor in the effect comparison parameter, determine the improvement level corresponding to the potential improvement factor, set the improvement level index corresponding to the improvement level, and generate the optimization plan corresponding to the electronic auxiliary material to be processed based on the improvement level index.

2. The method for intelligent optimization of processing parameters of electronic auxiliary materials according to claim 1, characterized in that: The collecting of real-time operation data corresponding to the preset processing equipment based on the initial processing parameters includes: Based on the initial processing parameters, setting a preset time interval for data collection corresponding to the processing equipment; Based on the time interval, collecting raw processing data corresponding to the preset processing equipment; Standardizing the format of the original processed data to obtain a standard data set; Analyze the operation phase corresponding to the data in the standard data set; Based on the operation stage, real-time operation data corresponding to the preset processing equipment is collected.

3. The method for intelligent optimization of processing parameters of electronic auxiliary materials according to claim 1, characterized in that: The step of generating a machining process curve corresponding to the core parameter subset includes: Extracting the time series corresponding to each parameter in the core parameter subset; Performing interpolation processing on the time series to obtain a complete time series; Based on the complete time series, drawing an initial curve sketch corresponding to the core parameter subset; Smoothing the initial curve sketch to obtain a smoothed processing curve; Marking key process nodes corresponding to the smoothing processing curve; Based on the key process nodes, a machining process curve corresponding to the core parameter subset is generated.

4. The method for intelligent optimization of processing parameters of electronic auxiliary materials according to claim 1, characterized in that: The step of performing slope analysis on the machining process curve to obtain a slope change sequence includes: Extracting discrete data points from the machining process curve; Sorting the discrete data points to obtain an ordered data point set; determining adjacent data points in the ordered set of data points; Calculating the initial slope value between the adjacent data points; Based on the initial slope value, a slope analysis is performed on the machining process curve to obtain a slope change sequence.

5. The method for intelligent optimization of processing parameters of electronic auxiliary materials according to claim 1, characterized in that: The step of determining the processing direction corresponding to the electronic auxiliary material to be processed based on the auxiliary material stability value includes: Determine the numerical range corresponding to the stability value of the auxiliary material; Based on the numerical range, dividing the graded stability zones corresponding to the stability values ​​of the auxiliary materials; Analyzing the preliminary processing direction corresponding to the graded stable area; Performing machining simulation on the preliminary machining direction to obtain machining simulation data; Based on the processing simulation data, a processing direction corresponding to the electronic auxiliary material to be processed is determined.

6. The method for intelligent optimization of processing parameters of electronic auxiliary materials according to claim 1, characterized in that: The step of comparing the effect data with preset target data to obtain effect comparison parameters includes: Identify the effect indicator item to which the effect data belongs; Reclassify the effect indicator items according to the classification framework of the preset target data to obtain a classified effect subset; Comparing the classification effect subset with the corresponding subset of preset target data to obtain a comparison difference; Based on the comparison difference, the effect data is compared with the preset target data to obtain effect comparison parameters.

7. The method for intelligent optimization of processing parameters of electronic auxiliary materials according to claim 1, characterized in that: The querying of the potential improvement factors in the effect comparison parameters includes: Analyzing abnormal fluctuation labels in the effect comparison parameters; Trace back the processing link corresponding to the abnormal fluctuation label; Based on the processing links, searching for the root causes of problems in the historical processing data; Extract the core problem factors corresponding to the root causes of the problems; Based on the core problem factors, potential improvement factors in the effect comparison parameters are queried.

8. An intelligent optimization system for processing parameters of electronic auxiliary materials, characterized in that: The system comprises: A subset extraction module is used to obtain electronic auxiliary materials to be processed, identify initial processing parameters corresponding to the electronic auxiliary materials to be processed, collect real-time operation data corresponding to preset processing equipment based on the initial processing parameters, classify the real-time operation data to obtain a classified data set, and extract a core parameter subset from the classified data set; The influence value calculation module is used to generate a machining process curve corresponding to the core parameter subset, perform slope analysis on the machining process curve to obtain a slope change sequence, identify a mutation point in the slope change sequence, and calculate a mutation influence value corresponding to the mutation point, wherein the calculation of the mutation influence value corresponding to the mutation point includes: The mutation impact value corresponding to the mutation point is calculated using the following formula: ； in, Indicates the mutation impact value corresponding to the mutation point, Represents the total number of influencing factors related to the mutation point, Indicates the quantitative index of influencing factors, Indicated in The influence degree value corresponding to each influencing factor is Indicated in The data weights corresponding to the influencing factors and the data related to the mutation point, Indicates the number of characteristic attributes corresponding to the mutation point, Indicates the number index of feature attributes, Indicates The characteristic quantization value corresponding to the characteristic attribute of each mutation point; A direction determination module is used to collect the fluctuation characteristics corresponding to the mutation impact value, identify the fluctuation range of the fluctuation characteristics at different processing stages, and calculate the auxiliary material stability value corresponding to the electronic auxiliary material to be processed based on the fluctuation range, wherein the calculation of the auxiliary material stability value corresponding to the electronic auxiliary material to be processed based on the fluctuation range includes: The auxiliary material stability value corresponding to the electronic auxiliary material to be processed is calculated using the following formula: ； in, Indicates the auxiliary material stability value corresponding to the electronic auxiliary material to be processed, Indicates the total number of fluctuation factors in the fluctuation range. represents the quantitative index of the volatility factor, Indicated in The fluctuation amplitude value corresponding to each fluctuation factor is Indicated in The phase value corresponding to each fluctuation factor is Indicates the number of lower limit factors related to the lower limit of the fluctuation range, represents the quantitative index of the lower limit factor, Indicates The lower limit quantitative value corresponding to the lower limit factor is represents the number of upper limit factors related to the upper limit of the fluctuation range, represents the quantitative index of the upper limit factor, Indicates The upper limit quantization value corresponding to the upper limit factor is used to determine the processing direction corresponding to the electronic auxiliary material to be processed based on the auxiliary material stability value; An effect comparison module is used to identify the processing adjustment strategy corresponding to the processing direction, monitor the effect data after the processing adjustment strategy is implemented in real time, compare the effect data with the preset target data, and obtain effect comparison parameters; The scheme generation module is used to query the potential improvement factor in the effect comparison parameter, determine the improvement level corresponding to the potential improvement factor, set the improvement level index corresponding to the improvement level, and generate the optimization scheme corresponding to the electronic auxiliary material to be processed based on the improvement level index.

Images