PCB production data real-time analysis method and system

Abstract

The invention relates to the technical field of PCB production, in particular to a PCB production data real-time analysis method and system, and the method comprises the following steps: collecting the size data and weight data of PCBs based on the production packaging process of the PCBs, employing a random forest algorithm, evaluating the whole stack efficiency of the PCBs, and carrying out the whole stack parameter optimization, and obtaining the whole stack efficiency optimization index. By analyzing the size and weight data of the PCB in real time, the stacking efficiency can be accurately evaluated and optimized by adopting a random forest algorithm, so that the resource utilization rate is increased, the production waste is reduced, the time sequence analysis is applied to the use data of the humidity card and the drying agent, the regulation and control of the production environment are finer, and the production efficiency is improved. The quality consistency and reliability of products in the production process are ensured, the operation data of the manipulator are analyzed through the CNN network, the operation efficiency is improved, the adaptability of the production line to emergencies is enhanced, the packaging process is optimized through real-time regression analysis of thermal parameters, and the packaging quality is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of PCB production, and in particular to a real-time analysis method and system for PCB production data. Background Art

[0002] PCB production technology involves all steps from designing, manufacturing to testing printed circuit boards (PCBs). Printed circuit boards are an indispensable part of electronic devices. PCBs provide physical support and electrical connections between electronic components, including the design of multi-layer PCBs, material selection, drawing of circuit diagrams, and the application of chemical and physical processes to manufacture PCBs. With the advancement of technology, PCB production is increasingly focused on improving production efficiency and reducing costs while ensuring product quality and reliability.

[0003] Among them, the real-time analysis method of PCB production data focuses on real-time collection and analysis of data in the PCB production process to optimize the production process and improve production efficiency. By using sensors, data acquisition and data analysis technology, it can instantly monitor various parameters on the production line, such as temperature, pressure, and current, etc., so as to detect anomalies in the production process in real time and make adjustments quickly, which not only helps to reduce the scrap rate in the production process, but also ensures the consistency and quality of the products, and improves the automation and intelligence level of the production line.

[0004] Existing technologies lack the ability to respond to real-time data feedback, resulting in untimely or inaccurate adjustments when production conditions or environmental parameters change. For example, although the operating parameters of the robot can be adjusted automatically, without the support of deep learning, its adjustment will not be optimized for complex or non-standard situations. Existing technologies are also insufficient in monitoring small changes in temperature and pressure in a timely manner, resulting in the packaging of products before the optimal packaging conditions are met, affecting product quality and hindering the maximum optimization of the production process. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a real-time analysis method and system for PCB production data.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: a real-time analysis method for PCB production data, comprising the following steps:

[0007] S1: Based on the production and packaging process of PCB boards, the size and weight data of PCB boards are collected, and the random forest algorithm is used to evaluate the stacking efficiency of PCB boards, and the stacking parameters are optimized to obtain the stacking efficiency optimization index;

[0008] S2: Based on the stacking efficiency optimization index, a time series analysis is performed on the usage data of the humidity card and the desiccant to evaluate the impact on the PCB board packaging environment, and according to the impact analysis results, the placement mechanism of the humidity card and the desiccant is adjusted to obtain the environmental control parameters;

[0009] S3: Based on the environmental control parameters, the operation data of the six-axis manipulator and the three-axis manipulator are analyzed, and the operation efficiency problems in the PCB board packaging process are identified by using the CNN network, and the manipulator control parameters are continuously monitored and adjusted to generate efficiency optimization configuration;

[0010] S4: Based on the efficiency optimization configuration, regression analysis is performed on the heat shrink packaging temperature data and the heat shrink packaging pressure data to determine the optimal thermal parameters, the optimal thermal parameters are applied to the packaging line, and the PCB board packaging process is monitored and adjusted in real time to obtain a production data analysis log.

[0011] The present invention is improved in that the steps of obtaining the optimization index of the stacking efficiency are specifically as follows:

[0012] S111: Based on the production and packaging process of PCB boards, collect the size data and weight data of PCB boards, merge the data, and build an integrated data set;

[0013] S112: Based on the integrated data set, the stacking efficiency of the PCB board is evaluated by a random forest algorithm, using the formula:

[0014]

[0015] The stacking efficiency evaluation result is obtained, where ED represents the stacking efficiency of the PCB board, and w i represents the weight of the i-th data point, RF(X i ) is the random forest for the i-th data point X i The efficiency output of , n is the total number of data points;

[0016] S113: According to the stacking efficiency evaluation result, stacking parameters are adjusted to optimize the stacking efficiency and obtain a stacking efficiency optimization index.

[0017] The present invention is improved in that the step of evaluating the impact on the PCB board packaging environment is specifically as follows:

[0018] S211: Based on the stacking efficiency optimization index, collect usage data of humidity cards and desiccants during PCB packaging, including usage type, quantity and duration, to obtain usage data records;

[0019] S212: Perform time series analysis on the usage data records to calculate the effect of the humidity card and the desiccant on the humidity of the packaging environment using the formula:

[0020]

[0021] The time series analysis results are obtained, where ΔHS represents the change in ambient humidity, hs i is the influence coefficient of the ith humidity card or desiccant, qs i is the usage of the ith humidity card or desiccant, α s is the environmental sensitivity adjustment factor, n s is the number of material types;

[0022] S213: Based on the time series analysis result, a comparative analysis is performed with the PCB board damage data to evaluate the effects of the humidity card and the desiccant, and obtain a packaging environmental impact assessment result.

[0023] The present invention is improved in that the step of obtaining the environmental control parameters is specifically as follows:

[0024] S221: According to the impact analysis result, adjusting the placement mechanism of the humidity card and the desiccant, including adjusting the placement amount and frequency of the humidity card and the desiccant, optimizing the humidity control of the PCB board packaging environment, and obtaining new humidity control parameters;

[0025] S222: Based on the new humidity control parameters, the PCB board packaging process is tested, the change of environmental humidity and the damage rate of the PCB board are monitored, and the environmental control parameters are obtained.

[0026] The present invention is improved in that the steps of analyzing the operation data are specifically as follows:

[0027] S311: Based on the environmental control parameters, collect the operation data of the six-axis and three-axis manipulators, including the operation speed, accuracy, and frequency of failure, to obtain a manipulator performance data set;

[0028] S312: Based on the robot performance data set, the CNN network is used to process the speed and accuracy data of the robot, and the impact of environmental parameter changes on the performance of the robot is evaluated using the formula:

[0029] RB i =a Q +b Q ·SF i +c Q PF i

[0030] Identify key influencing factors and operational efficiency issues and obtain robot analysis results, among which RB i represents the robot response time of the ith data point, SF i is the robot operation speed recorded at the ith data point, PF iis the robot operation accuracy recorded at the i-th data point, a Q is a constant term, b Q is the velocity coefficient, c Q is the accuracy coefficient.

[0031] The present invention is improved in that the steps of obtaining the efficiency optimization configuration are specifically as follows:

[0032] S321: regularly collect the operation data of the six-axis and three-axis manipulators, including the operation speed, accuracy and frequency of failure, monitor the performance effect of the current manipulator control parameters, and obtain a monitoring data set;

[0033] S322: Analyze the monitoring data set, adjust the robot control parameters, including speed setting or accuracy adjustment, and re-evaluate the performance of the robot, compare the operation data before and after the adjustment, determine whether the target efficiency is achieved, and obtain the efficiency optimization configuration.

[0034] The present invention is improved in that the step of determining the optimal thermal parameters is specifically as follows:

[0035] S411: Based on the efficiency optimization configuration, collect temperature and pressure data during heat shrink packaging, including values ​​under various packaging conditions, to obtain a temperature and pressure data set;

[0036] S412: Apply regression analysis to process the temperature and pressure data set, using the formula:

[0037] VP opt =a O +b O VT+c O VPr

[0038] Analyze the influence of parameters on packaging quality and determine the optimal thermal parameters, among which VP opt represents the optimal packaging performance, VT is the temperature setting during packaging, VPr is the pressure applied during packaging, and a O is a constant term, b O is the regression coefficient of temperature, c O is the regression coefficient of pressure.

[0039] The present invention is improved in that the steps of obtaining the production data analysis log are specifically as follows:

[0040] S421: Based on the optimal thermal parameters, the PCB board packaging process is monitored in real time, and the real-time data of temperature and pressure and the associated packaging data are collected to obtain real-time monitoring data records;

[0041] S422: Analyze the collected real-time monitoring data records to evaluate data trends and anomalies using the formula:

[0042] LH eff =δ M ·(WH t -WH t-1 )+γ M ·PH eff

[0043] Analyze the impact on production efficiency and obtain production data analysis log, where LH eff Indicates log efficiency, WH t Indicates the working temperature parameter at the current time point, WH t-1 Indicates the operating temperature parameter at the previous time point, PH eff represents the process efficiency, δ M and γ M is the adjustment factor.

[0044] A PCB production data real-time analysis system, the system comprising:

[0045] The stacking efficiency module collects PCB size and weight data based on the production and packaging process of PCB boards, uses the random forest algorithm to analyze the stacking efficiency of PCB boards, adjusts the stacking parameters, and obtains the stacking efficiency optimization index;

[0046] The environmental control module performs time series analysis on the usage data of the humidity card and the desiccant based on the overall stacking efficiency optimization index, evaluates the impact on the PCB board packaging environment, and adjusts the placement mechanism of the humidity card and the desiccant according to the impact analysis results to obtain the environmental control parameters;

[0047] The robot optimization module analyzes the operation data of the six-axis robot and the three-axis robot based on the environmental control parameters, uses the CNN network to identify the operation efficiency problems in the PCB board packaging process, monitors and adjusts the robot control parameters, and generates efficiency optimization configuration;

[0048] The thermal parameter setting module performs regression analysis on the heat shrink packaging temperature data and the heat shrink packaging pressure data based on the efficiency optimization configuration to determine the optimal thermal parameters;

[0049] The monitoring and recording module applies the optimal thermal parameters to the packaging line, monitors and adjusts the packaging process of the PCB board in real time, and obtains a production data analysis log.

[0050] Compared with the prior art, the advantages and positive effects of the present invention are:

[0051] In the present invention, by real-time analysis of the size and weight data of the PCB board, the random forest algorithm is used to accurately evaluate and optimize the stacking efficiency, thereby improving resource utilization and reducing production waste. Time series analysis is applied to the usage data of the humidity card and the desiccant to make the regulation of the production environment more refined, ensuring the quality consistency and reliability of the product during the production process. The CNN network is used to analyze the operation data of the robot, which not only improves the operating efficiency but also enhances the adaptability of the production line to emergencies. The real-time regression analysis of thermal parameters optimizes the packaging process, ensures the packaging quality, and reduces rework and waste generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A flow chart of a method for real-time analysis of PCB production data is proposed for the present invention;

[0053] Figure 2 This is a flow chart for obtaining the optimization index of the stacking efficiency in the present invention;

[0054] Figure 3 A flow chart of evaluating the impact on the PCB board packaging environment in the present invention;

[0055] Figure 4 This is a flow chart for obtaining environmental control parameters in the present invention;

[0056] Figure 5 A flow chart for analyzing operation data in the present invention;

[0057] Figure 6 A flowchart for obtaining the efficiency optimization configuration in the present invention;

[0058] Figure 7 is a flow chart for determining the optimal thermal parameters in the present invention;

[0059] Figure 8 This is a flow chart for obtaining the production data analysis log in the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0061] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0062] Example

[0063] See also Figure 1 The present invention provides a technical solution: a real-time analysis method for PCB production data, comprising the following steps:

[0064] S1: Based on the production and packaging process of PCB boards, the size and weight data of PCB boards are collected, and the random forest algorithm is used to evaluate the stacking efficiency of PCB boards, and the stacking parameters are optimized to obtain the stacking efficiency optimization index;

[0065] S2: Based on the whole stacking efficiency optimization index, the time series analysis of the use data of humidity cards and desiccant is carried out to evaluate the impact on the PCB packaging environment. According to the impact analysis results, the placement mechanism of humidity cards and desiccant is adjusted to obtain the environmental control parameters;

[0066] S3: Based on the environmental control parameters, the operation data of the six-axis robot and the three-axis robot are analyzed, and the CNN network is used to identify the operational efficiency problems in the PCB board packaging process, and the robot control parameters are continuously monitored and adjusted to generate efficiency optimization configuration;

[0067] S4: Based on the efficiency optimization configuration, regression analysis is performed on the heat shrink packaging temperature data and heat shrink packaging pressure data to determine the optimal thermal parameters. The optimal thermal parameters are applied to the packaging line, and the PCB board packaging process is monitored and adjusted in real time to obtain the production data analysis log.

[0068] The overall stack efficiency optimization indicators include stacking height standard, area utilization, and weight distribution balance. The environmental control parameters include humidity maintenance range, desiccant absorption capacity, and humidity recovery time. The efficiency optimization configuration includes response time optimization results, automatic fault diagnosis results, and energy efficiency ratio. The production data analysis log includes temperature monitoring indicators, pressure change data, and adjustment feedback frequency.

[0069] See also Figure 2 , the specific steps for obtaining the whole stack efficiency optimization index are:

[0070] S111: Based on the production and packaging process of PCB boards, collect the size data and weight data of PCB boards, merge the data, and build an integrated data set;

[0071] The size data is detected by automated measuring equipment, and the weight data is obtained through an online weighing system. The measuring equipment includes a laser ranging sensor and a high-precision electronic scale. The data collected by the sensor is stored in the form of raw signals, and the raw signals are cleaned to delete duplicate values ​​and noise data. The cleaned data is stored in an integrated data pool in a standard format. At the same time, the stored data is classified and indexed according to board number, batch and timestamp for subsequent processing, and finally the integration of PCB board size and weight data is completed to form an integrated data set for analysis.

[0072] S112: Based on the integrated data set, the random forest algorithm is used to evaluate the stacking efficiency of PCB boards, using the formula:

[0073]

[0074] The stacking efficiency evaluation result is obtained, where ED represents the stacking efficiency of the PCB board, and w i represents the weight of the i-th data point, reflecting the importance of the data point in the evaluation of the stacking efficiency. i ) is the random forest for the i-th data point X i Efficiency output, X i Include all relevant features of the data point, such as size and weight, where n is the total number of data points;

[0075] There are 3 data points of PCB boards, with weights w1=0.5, w2=1.5, w3=0.8 respectively. The efficiency output of random forest for the data points is RF(X1)=0.75, RF(X2)=0.85, RF(X3)=0.65 respectively. Substitute into the formula:

[0076]

[0077] The results show that by considering the specific weights and efficiencies of different PCB boards, the weighted stack efficiency can be obtained to be 1.23, indicating that the overall efficiency is relatively high, which improves the accuracy and adaptability of the evaluation.

[0078] S113: According to the stacking efficiency evaluation result, adjusting the stacking parameters, optimizing the stacking efficiency, and obtaining the stacking efficiency optimization index;

[0079] Based on the stacking efficiency evaluation data, key influencing factors are extracted, such as stacking height, plate arrangement, vertical pressure and other parameters, and sensitivity analysis is performed on the influencing factors to identify the parameters that have the greatest impact on efficiency fluctuations. Combined with on-site test data, the stacking height and arrangement method are optimized, and the impact of different parameter combinations on the stacking efficiency is tested. Regression analysis is used to quantify the effect of adjustment on improving efficiency, determine the optimal parameter combination, input the optimized parameter values ​​into the control system of the production line, adjust the stacking settings of the production equipment, and monitor the adjusted efficiency changes in real time to form an optimized stacking efficiency indicator.

[0080] See also Figure 3 , the specific steps for evaluating the impact on the PCB packaging environment are:

[0081] S211: Based on the whole stacking efficiency optimization index, the usage data of humidity cards and desiccants in the PCB packaging process are collected, including the usage type, quantity and duration, to obtain usage data records;

[0082] The usage type, quantity and duration of humidity cards and desiccants are obtained in real time. A unique identifier needs to be set during the data collection process to distinguish the usage records of different batches. All data are summarized after collection. By calling the data interface, the type of humidity card, moisture absorption capacity, and desiccant activity are classified and labeled, and the correlation analysis of various data is supplemented in combination with the time node. Further generate usage data records including the frequency, duration and quantity statistics of various humidity control materials. This record provides direct data support for subsequent analysis.

[0083] S212: Perform time series analysis on the usage data records and calculate the effect of humidity card and desiccant on the packaging environment humidity using the formula:

[0084]

[0085] The time series analysis results are obtained, where ΔHS represents the change in ambient humidity, hs i is the influence coefficient of the ith humidity card or desiccant, qs i is the usage of the ith humidity card or desiccant, α s is the environmental sensitivity adjustment factor, which is used to adjust the calculation results to better reflect the effect of humidity control measures under specific environmental conditions, n s is the number of material types;

[0086] There are three different humidity control materials. The usage and influence coefficient of each material are as follows: hs1 = 0.3, qs1 = 50, hs2 = 0.45, qs2 = 30, hs3 = 0.25, qs3 = 20, and the environmental sensitivity adjustment coefficient α s =1.2, the calculation process is:

[0087] ΔHS=1.2×[(0.3×50)+(0.45×30)+(0.25×20)]

[0088] ΔHS=1.2×[15+13.5+5]

[0089] ΔHS=1.2×33.5

[0090] ΔHS=40.2

[0091] The results show that considering the use of various humidity control materials, the change in environmental humidity is 40.2, indicating that under the current humidity control strategy, humidity control measures have a significant impact on the environment, providing a direct basis for adjusting the strategy.

[0092] S213: Based on the time series analysis results, a comparative analysis is performed with the PCB board damage data to evaluate the effects of the humidity card and the desiccant, and obtain the packaging environmental impact assessment results;

[0093] By analyzing the relationship between humidity changes in the packaging environment and PCB damage data, the humidity change data and the PCB damage rate are matched item by item. By statistically analyzing the damage rate corresponding to humidity changes in historical data, the impact of humidity changes on the protection performance of PCB boards is analyzed. By constructing a tabular comparative analysis template, the damage probability under different humidity ranges is grouped and evaluated. Combined with the specific failure type data in the damage record, the improvement effect of humidity control materials on the humidity in the packaging environment is extracted, and a summary analysis table on the use effect of humidity cards and desiccant is generated to form a complete packaging environmental impact assessment result.

[0094] See also Figure 4 , the specific steps for obtaining environmental control parameters are:

[0095] S221: According to the impact analysis results, the delivery mechanism of the humidity card and the desiccant is adjusted, including the delivery amount and frequency of the humidity card and the desiccant, so as to optimize the humidity control of the PCB board packaging environment and obtain new humidity control parameters;

[0096] Adjustment of the humidity card and desiccant delivery mechanism requires comprehensive consideration of multiple factors, including the humidity baseline value of the use environment, the moisture absorption rate of different types of humidity control materials, and the sensitivity of the PCB board to humidity fluctuations. The delivery amount is adjusted by analyzing the performance parameters of the humidity card and desiccant. The specific adjustment process includes calculating the daily fluctuation range of the humidity baseline value, selecting the appropriate humidity card type according to the fluctuation range, and estimating the daily delivery amount according to the moisture absorption rate. Subsequently, the delivery frequency of the desiccant is optimized according to the actual operation time of the packaging line to generate the humidity control parameter configuration.

[0097] S222: Based on the new humidity control parameters, the PCB board packaging process is tested, the change of environmental humidity and the damage rate of the PCB board are monitored, and the environmental control parameters are obtained;

[0098] Test the environmental changes during the PCB packaging process. First, monitor the actual humidity changes after the use of humidity cards and desiccant, compare the humidity change data with the target value in the humidity control parameters, and evaluate the actual effect of humidity cards and desiccant. Secondly, collect the integrity data of the PCB boards after packaging, record the damage rate of the boards affected by humidity control by analyzing the data, and compare the changes in damage rate before and after adjustment to determine the effectiveness of the new humidity control parameters. Finally, optimize the environmental control parameters according to the experimental data to ensure the adaptability and operability of the optimized parameters in practical applications.

[0099] See also Figure 5 , the specific steps for analyzing the running data are:

[0100] S311: Based on the environmental control parameters, the operation data of the six-axis and three-axis manipulators are collected, including the operation speed, accuracy, and frequency of failures, to obtain a manipulator performance data set;

[0101] First, the operation data of the six-axis and three-axis manipulators are collected in real time through sensors. The data content covers core indicators such as operation speed, accuracy and fault frequency. During the collection process, each operation record of the manipulator is divided into independent data points. Each data point records the operation time of the manipulator, the deviation value of the motion trajectory and the type of fault generated during the operation. To ensure data integrity, a redundant collection strategy is used to cross-validate key operation data. At the same time, data with sensor abnormalities or large errors are eliminated. The elimination standard is based on the setting of operation time deviation exceeding the normal range. Through this process, the manipulator performance data set is obtained, which contains operation performance records under different environmental control parameters, providing multi-dimensional data support required for subsequent analysis.

[0102] S312: Based on the robot performance data set, the CNN network is used to process the robot speed and accuracy data to evaluate the impact of environmental parameter changes on the robot performance. The formula is:

[0103] RB i =a Q +b Q ·SF i +c Q PF i

[0104] Identify key influencing factors and operational efficiency issues and obtain robot analysis results, among which RB i represents the robot response time of the ith data point, SFi is the robot operation speed recorded at the ith data point, PF i is the robot operation accuracy recorded at the i-th data point, a Q is a constant term, which can be regarded as the basic response time, b Q is the speed factor, indicating the speed SF i Response time RB i The impact of Q Is the accuracy coefficient, indicating the accuracy PF i Response time RB i The impact of

[0105] The movement speed of the manipulator in a certain environment is 120 mm / s, the accuracy is 98%, the basic response time is 0.5 seconds, the speed influence coefficient is 0.05 seconds, and the accuracy influence coefficient is -0.01 seconds. Substitute it into the formula for calculation:

[0106] RB i =0.5+0.05·120+(-0.01)·98

[0107] RB i =0.5+6-0.98=5.52

[0108] The results show that at this speed and accuracy, the robot's response time is 5.52 seconds, demonstrating how adjusting speed and accuracy to optimize response time can directly help improve production efficiency and reduce errors.

[0109] See also Figure 6 , the specific steps for obtaining the efficiency optimization configuration are:

[0110] S321: regularly collect the operation data of the six-axis and three-axis manipulators, including the operation speed, accuracy and frequency of failure, monitor the performance effect of the current manipulator control parameters, and obtain a monitoring data set;

[0111] The data of each operation is recorded in real time by sensors installed on the robot, and stored in categories by time, robot type and task batch. Invalid data and noise are then cleaned up, and the speed, accuracy and failure rate data are formatted and stored in a unified manner for subsequent analysis. During the monitoring period, performance changes under different environmental conditions are marked and annotated to form data with environmental relevance, thus obtaining a monitoring data set covering different operating conditions and performance performances.

[0112] S322: Analyze the monitoring data set, adjust the robot control parameters, including speed setting or accuracy adjustment, and re-evaluate the performance of the robot, compare the operation data before and after the adjustment, determine whether the target efficiency is achieved, and obtain the efficiency optimization configuration;

[0113] Analyze the speed and accuracy data, and perform comparative processing to determine the changing trend of the robot's operating efficiency. First, group and calculate each control parameter, including calculating its mean and variance according to the speed range and accuracy range. Then compare the failure frequency of each group, analyze the impact of the speed and accuracy ratio on the operating efficiency, and then perform a difference analysis on the robot's operating data before and after adjustment to determine whether the adjustment is effective. When the efficiency difference exceeds the set threshold, further adjust the control parameters and retest to obtain the efficiency optimization configuration after performance improvement.

[0114] See also Figure 7 , the specific steps for determining the optimal thermal parameters are:

[0115] S411: Based on the efficiency optimization configuration, collect temperature and pressure data in the heat shrink packaging process, including values ​​under various packaging conditions, and obtain temperature and pressure data sets;

[0116] Multiple groups of test conditions for heat shrink packaging equipment were set up, and the temperature and pressure data of the packaging line were recorded under each group of conditions. The temperature and pressure readings were obtained through real-time monitoring sensors installed on the packaging equipment. Then, the data filtering method was used to eliminate noise and invalid data, and the data were classified and stored. The classification criteria included packaging material type, production batch, and equipment type. Each group of data points recorded specific temperature values, pressure values, and their corresponding timestamps. The accuracy and representativeness of the data were ensured through repeated tests. The temperature and pressure data of each group of tests were integrated to obtain the temperature and pressure data sets.

[0117] S412: Apply regression analysis to the temperature and pressure data sets using the formula:

[0118] VP opt =a O +b O VT+c O VPr

[0119] Analyze the influence of parameters on packaging quality and determine the optimal thermal parameters, among which VP opt It indicates the optimal packaging performance, reflecting the optimal packaging quality that can be achieved under a specific temperature and pressure combination. VT is the temperature setting during the packaging process, which directly affects the heat shrinkage effect and packaging quality. VPr is the pressure applied during the packaging process, which is key to the shrinkage rate and sealing strength of the material. O is a constant term, representing the baseline packaging effect, i.e., the default packaging performance when there is no temperature and pressure change, b O is the regression coefficient of temperature, indicating the effect of temperature change on packaging performance VP opt The degree of influence, c O is the regression coefficient of pressure, indicating the effect of pressure change on packaging performance VP optthe extent of the impact;

[0120] Under a specific set of packaging parameters, the measured temperature VT is 150°C, the pressure VPr is 5 bar, and the constant term a O The temperature coefficient b was determined to be 0.5. O is 0.03, the pressure coefficient c O is 0.02, and the optimal packaging performance is calculated according to the formula:

[0121] VP opt =0.5+0.03·150+0.02·5=0.5+4.5+0.1=5.1

[0122] The results show that at this specific temperature and pressure, a packaging performance index of 5.1 can be achieved, which reflects the overall quality and efficiency of the packaging, indicating that the effectiveness of the packaging process can be significantly improved by optimizing the temperature and pressure settings.

[0123] See also Figure 8 , the specific steps for obtaining production data analysis logs are:

[0124] S421: Based on the optimal thermal parameters, the PCB board packaging process is monitored in real time, and the real-time data of temperature and pressure and the associated packaging data are collected to obtain real-time monitoring data records;

[0125] Collect real-time data of temperature and pressure and associated packaging effect data. Use temperature sensors and pressure sensors to record temperature and pressure changes every second, and record the sealing strength and material integrity after packaging. After each packaging cycle, classify the data by timestamp, packaging batch and product number, and perform preliminary data cleaning operations, including removing invalid readings at sensor failure points and calculating outliers in the data range. The processed data is then integrated into a real-time monitoring data record covering the entire production cycle, which includes time series data of all key parameters and their correlation with packaging effects.

[0126] S422: Analyze the collected real-time monitoring data records and evaluate data trends and anomalies using the formula:

[0127] LH eff =δ M ·(WH t -WH t-1 )+γ M ·PH eff

[0128] Analyze the impact on production efficiency and obtain production data analysis log, where LH effRepresents log efficiency, which is used to measure the changes and optimization of packaging process efficiency in production data analysis logs. t Indicates the working temperature parameters at the current time point, including temperature and pressure, etc., reflecting the actual operating conditions of the current packaging process. t-1 Indicates the working temperature parameters at the previous time point, including temperature and pressure, etc., which are used to compare with the current data and analyze the trend of parameter changes. eff Represents process efficiency, used to quantify the efficiency level in the production process and evaluate the performance of the overall production line, δ M and γ M is the adjustment coefficient, which is used to adjust the contribution of different factors to efficiency;

[0129] If the operating temperature parameter measured at two consecutive time points is WH t =75℃ and WH t-1 =70℃, process efficiency PH eff =0.95, adjustment coefficient δ M = 0.1 and γ M =0.85, then substitute it into the formula and calculate as follows:

[0130] LH eff =0.1·(75-70)+0.85·0.95

[0131] LH eff =0.1·5+0.8075=0.5+0.8075=1.3075

[0132] The results show that during the observation period, the log value of production efficiency increased by 1.3075 by fine-tuning the temperature setting, indicating that subtle adjustments to the production environment can significantly improve the efficiency of the production process.

[0133] A real-time analysis system for PCB production data, the system comprising:

[0134] The stacking efficiency module collects PCB size and weight data based on the production and packaging process of PCB boards, uses the random forest algorithm to analyze the stacking efficiency of PCB boards, adjusts the stacking parameters, and obtains the stacking efficiency optimization index;

[0135] The environmental control module conducts time series analysis on the usage data of humidity cards and desiccants based on the whole stack efficiency optimization index, evaluates the impact on the PCB packaging environment, and adjusts the placement mechanism of humidity cards and desiccants according to the impact analysis results to obtain environmental control parameters;

[0136] The robot optimization module analyzes the operating data of the six-axis robot and the three-axis robot based on the environmental control parameters, uses the CNN network to identify the operational efficiency problems in the PCB board packaging process, and monitors and adjusts the robot control parameters to generate efficiency optimization configuration;

[0137] The thermal parameter setting module performs regression analysis on the heat shrink packaging temperature data and heat shrink packaging pressure data based on efficiency optimization configuration to determine the optimal thermal parameters;

[0138] The monitoring and recording module applies the optimal thermal parameters to the packaging line, monitors and adjusts the packaging process of the PCB board in real time, and obtains a production data analysis log.

[0139] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A real-time analysis method for PCB production data, characterized in that: The following steps are involved: Based on the production and packaging process of PCB boards, the size and weight data of PCB boards are collected, and the random forest algorithm is used to evaluate the stacking efficiency of PCB boards, and the stacking parameters are optimized to obtain the stacking efficiency optimization index; Based on the overall stacking efficiency optimization index, a time series analysis is performed on the usage data of the humidity card and the desiccant to evaluate the impact on the PCB board packaging environment, and according to the impact analysis results, the placement mechanism of the humidity card and the desiccant is adjusted to obtain the environmental control parameters; Based on the environmental control parameters, the operation data of the six-axis manipulator and the three-axis manipulator are analyzed, and the CNN network is used to identify the operation efficiency problems in the PCB board packaging process, and the manipulator control parameters are continuously monitored and adjusted to generate efficiency optimization configuration; Based on the efficiency optimization configuration, regression analysis is performed on the heat shrink packaging temperature data and the heat shrink packaging pressure data to determine the optimal thermal parameters, the optimal thermal parameters are applied to the packaging line, and the PCB board packaging process is monitored and adjusted in real time to obtain a production data analysis log.

2. The real-time analysis method for PCB production data according to claim 1, characterized in that: The steps for obtaining the stacking efficiency optimization index are specifically as follows: Based on the production and packaging process of PCB boards, the size and weight data of PCB boards are collected, the data are merged, and an integrated data set is constructed; Based on the integrated data set, the stacking efficiency of PCB boards is evaluated by random forest algorithm using the formula: The stacking efficiency evaluation result is obtained, where ED represents the stacking efficiency of the PCB board, and w i represents the weight of the i-th data point, RF(X i ) is the random forest for the i-th data point X i The efficiency output of , n is the total number of data points; According to the stacking efficiency evaluation result, the stacking parameters are adjusted to optimize the stacking efficiency and obtain the stacking efficiency optimization index.

3. The real-time analysis method for PCB production data according to claim 1, characterized in that: The steps of evaluating the impact on the PCB packaging environment are specifically as follows: Based on the stacking efficiency optimization index, the usage data of humidity cards and desiccants in the PCB packaging process are collected, including the usage type, quantity and duration, to obtain usage data records; The usage data records are analyzed in time series to calculate the effect of humidity card and desiccant on the humidity of packaging environment using the formula: The time series analysis results are obtained, where ΔHS represents the change in ambient humidity, hs i is the influence coefficient of the ith humidity card or desiccant, qs i is the usage of the ith humidity card or desiccant, α s is the environmental sensitivity adjustment factor, n s is the number of material types; Based on the time series analysis results, a comparative analysis is performed with the PCB board damage data to evaluate the effects of the humidity card and desiccant, and obtain the packaging environmental impact assessment results.

4. The real-time analysis method for PCB production data according to claim 1, characterized in that: The steps for obtaining the environmental control parameters are specifically as follows: According to the impact analysis results, the delivery mechanism of the humidity card and the desiccant is adjusted, including the delivery amount and frequency of the humidity card and the desiccant, so as to optimize the humidity control of the PCB board packaging environment and obtain new humidity control parameters; Based on the new humidity control parameters, the PCB board packaging process is tested, the change of environmental humidity and the damage rate of PCB boards are monitored, and the environmental control parameters are obtained.

5. The real-time analysis method for PCB production data according to claim 1, characterized in that: The steps of analyzing the operation data are specifically as follows: Based on the environmental control parameters, the operation data of the six-axis and three-axis manipulators are collected, including the operation speed, accuracy, and frequency of failures, to obtain a manipulator performance data set; Based on the robot performance data set, the CNN network is used to process the speed and accuracy data of the robot, and the impact of environmental parameter changes on the performance of the robot is evaluated using the formula: RB i =a Q +b Q ·SF i +c Q ·PF i Identify key influencing factors and operational efficiency issues and obtain robot analysis results, among which RB i represents the robot response time of the ith data point, SF i is the robot operation speed recorded at the ith data point, PF i is the robot operation accuracy recorded at the i-th data point, a Q is a constant term, b Q is the velocity coefficient, c Q is the accuracy coefficient.

6. The real-time analysis method for PCB production data according to claim 1, characterized in that: The steps for obtaining the efficiency optimization configuration are specifically as follows: Regularly collect the operation data of six-axis and three-axis manipulators, including operation speed, accuracy and frequency of failures, monitor the performance of current manipulator control parameters, and obtain monitoring data sets; Analyze the monitoring data set, adjust the robot control parameters, including speed setting or accuracy adjustment, and re-evaluate the performance of the robot, compare the operation data before and after the adjustment, determine whether the target efficiency is achieved, and obtain the efficiency optimization configuration.

7. The real-time analysis method for PCB production data according to claim 1, characterized in that: The steps for determining the optimal thermal parameters are specifically as follows: Based on the efficiency optimization configuration, collecting temperature and pressure data during heat shrink packaging, including values ​​under various packaging conditions, to obtain a temperature and pressure data set; Regression analysis was applied to the temperature and pressure data sets using the formula: VP opt =a O +b O ·VT+c O ·VPr Analyze the influence of parameters on packaging quality and determine the optimal thermal parameters, among which VP opt represents the optimal packaging performance, VT is the temperature setting during packaging, VPr is the pressure applied during packaging, and a O is a constant term, b O is the regression coefficient of temperature, c O is the regression coefficient of pressure.

8. The real-time analysis method for PCB production data according to claim 1, characterized in that: The steps for obtaining the production data analysis log are specifically as follows: Based on the optimal thermal parameters, the PCB board packaging process is monitored in real time, and real-time data of temperature and pressure and related packaging data are collected to obtain real-time monitoring data records; The collected real-time monitoring data records are analyzed to evaluate data trends and anomalies using the formula: LH eff =δ M ·(WH t -WH t-1 )+γ M ·PH eff Analyze the impact on production efficiency and obtain production data analysis log, where LH eff Indicates log efficiency, WH t Indicates the working temperature parameter at the current time point, WH t-1 Indicates the operating temperature parameter at the previous time point, PH eff represents the process efficiency, δ M and γ M is the adjustment factor.

9. A real-time analysis system for PCB production data, characterized in that: According to the method for real-time analysis of PCB production data according to any one of claims 1 to 8, the system comprises: The stacking efficiency module collects PCB size and weight data based on the production and packaging process of PCB boards, uses the random forest algorithm to analyze the stacking efficiency of PCB boards, adjusts the stacking parameters, and obtains the stacking efficiency optimization index; The environmental control module performs time series analysis on the usage data of the humidity card and the desiccant based on the overall stacking efficiency optimization index, evaluates the impact on the PCB board packaging environment, and adjusts the placement mechanism of the humidity card and the desiccant according to the impact analysis results to obtain the environmental control parameters; The robot optimization module analyzes the operation data of the six-axis robot and the three-axis robot based on the environmental control parameters, uses the CNN network to identify the operation efficiency problems in the PCB board packaging process, monitors and adjusts the robot control parameters, and generates efficiency optimization configuration; The thermal parameter setting module performs regression analysis on the heat shrink packaging temperature data and the heat shrink packaging pressure data based on the efficiency optimization configuration to determine the optimal thermal parameters; The monitoring and recording module applies the optimal thermal parameters to the packaging line, monitors and adjusts the packaging process of the PCB board in real time, and obtains a production data analysis log.

Images