Intelligent battery cover feeding and vulcanization control system

Abstract

The application relates to the technical field of automation control, in particular to an intelligent battery cover feeding and vulcanization control system, which comprises a parameter extraction module, a nonlinear modeling module, an optimal path adjustment module, a real-time feedback module and a multi-target optimization module.In the application, the changes of temperature, pressure and time in the vulcanization process are collected and analyzed in real time, a core parameter set is extracted, abnormal data is accurately screened, a nonlinear correlation mapping is constructed, the depth optimization of the hysteresis and dynamic feedback among parameters is realized, the dynamic adjustment path and the real-time feedback trend are combined, the temperature and pressure matching is effectively controlled, the accurate connection of the vulcanization conditions and the process flow is ensured, the dynamic optimization path is analyzed and adjusted according to the trend and parameter value, the deviation range in the production process is significantly reduced, the process consistency and quality stability are improved, the multi-target joint optimization further balances the efficiency and quality, optimizes the resource utilization rate, and reduces the influence of production fluctuation on product performance.

Description

Technical Field

[0001] The present invention relates to the field of automation control technology, and in particular to an intelligent battery cover loading and unloading and vulcanization control system. Background Art

[0002] The field of automated control technology encompasses various control systems and related equipment and methods used to achieve automated industrial, commercial, and civil operations. The core of this technical field is the precise control of various production processes, operational procedures, and equipment operating states through sensing, analysis, and control to achieve efficient, safe, and stable operation. Within this field, various technologies, including mechanical control, electrical control, computer control, and embedded systems, are widely used, and various automation tasks are accomplished through a combination of hardware and software. Systematic research in the field of automated control technology encompasses control system architecture design, motion control, logic control, monitoring data acquisition, and actuator drive, involving applications such as industrial robots, production lines, automated testing, and logistics systems.

[0003] Among them, the intelligent battery cover loading and unloading and vulcanization control system refers to a comprehensive system for realizing automatic loading and unloading of battery covers and vulcanization process control. The subject of this patent is aimed at the demand for automated operation of battery covers during battery production. It uses mechanical devices to achieve precise positioning and automatic transportation of battery covers, and uses control devices to monitor and adjust the temperature, pressure and time during the vulcanization process in real time. Its specific contents include collecting key process parameters through sensors, using control systems to complete the setting and adjustment of vulcanization conditions, and using actuators to drive and feedback the loading and unloading actions of battery covers. The entire system is based on closed-loop control and ensures smooth connection and stable operation of each link by synchronously coordinating the loading and unloading and vulcanization processes.

[0004] Existing technologies lack the ability to analyze parameter fluctuations, making it impossible to accurately extract and filter outliers during the vulcanization process, which can easily lead to data deviations that affect process stability. The lack of dynamic interactive adjustment of temperature and pressure prevents timely response to parameter changes, resulting in insufficient control accuracy during the process. Feedback mechanisms suffer from delays, making it difficult to correct abnormal conditions in a timely manner, reducing production efficiency and quality consistency. Target optimization is limited to a single indicator and cannot effectively balance the dynamic demands of quality and efficiency. Resource utilization is low, and the connection between process links is not smooth, which can easily lead to unstable operation or inefficiency. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent battery cover loading and unloading and vulcanization control system.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solutions: an intelligent battery cover loading and unloading and vulcanization control system includes:

[0007] The parameter extraction module extracts fluctuation interval data based on the temperature, pressure, and curing time values ​​of the battery cover collected during the curing process. It filters out abnormal values ​​within the offset range and calculates the fluctuation trend interval based on the time value to obtain the core parameter set of the battery cover.

[0008] The nonlinear modeling module calculates the hysteresis and feedback between parameter groups based on the temperature variation range, pressure variation range and fluctuation trend interval in the battery cover core parameter set, extracts the hysteresis coefficient and dynamic offset, and generates the battery cover nonlinear parameter mapping coefficient by calculating the nonlinear coefficient and variation trend;

[0009] The optimal path adjustment module extracts the adjustment trend values ​​of the real-time temperature change rate and the pressure change rate based on the nonlinear parameter mapping coefficient of the battery cover, analyzes the offset relationship between the temperature change trend and the pressure, calculates the parameter combination of the adjustment trend and the matching coefficient, and generates the dynamic adjustment path coefficient of the battery cover;

[0010] The real-time feedback module dynamically adjusts the path coefficient of the battery cover, extracts the real-time temperature value, pressure value and time value of the vulcanization stage, calculates the difference between the current temperature deviation and the target temperature, calculates the instantaneous parameter offset based on the pressure and time values, analyzes the feedback rate distribution trend, and generates the battery cover parameter feedback rate distribution value;

[0011] The multi-objective optimization module extracts the deviation range of the efficiency target value and the quality target value in the vulcanization stage based on the feedback rate distribution value of the battery cover parameters and the dynamic adjustment path coefficient of the battery cover, analyzes the target deviation value and the feedback rate distribution trend, analyzes the dynamic deviation distribution through the joint trend value, and generates the multi-objective optimization adjustment value of the battery cover.

[0012] The core parameter set of the battery cover includes the temperature change range, the pressure change range, and the fluctuation trend interval; the nonlinear parameter mapping coefficient of the battery cover includes the hysteresis coefficient, the dynamic offset, and the nonlinear coefficient; the dynamic adjustment path coefficient of the battery cover includes the real-time temperature change rate adjustment trend value, the real-time pressure change rate adjustment trend value, and the parameter sum value; the battery cover parameter feedback rate distribution value includes the current temperature deviation, the target temperature difference, and the instantaneous parameter offset; the battery cover multi-objective optimization adjustment value includes the efficiency target value deviation range, the quality target value deviation range, and the dynamic deviation distribution.

[0013] As a further solution of the present invention, the steps for obtaining the battery cover core parameter set are specifically as follows:

[0014] Extract the temperature and pressure values ​​of the battery cover during the vulcanization process, differentiate sampling segments according to the vulcanization time, calculate the temperature and pressure changes within the time range, filter the temperature and pressure fluctuation ranges in each time period, and establish the initial temperature and pressure fluctuation data sets;

[0015] Using the initial temperature fluctuation data set and the pressure fluctuation data set, calculating the difference between the maximum and minimum values ​​of multiple fluctuation intervals, filtering out-of-range data based on the difference and comparing it with a set offset threshold, eliminating abnormal values ​​outside the offset range, and generating a filtered fluctuation interval data set;

[0016] From the filtered fluctuation range data set, calculate the fluctuation trend corresponding to each time value, and determine the trend weight by combining the fluctuation trend with the time weight, using the formula:

[0017] ;

[0018] Get the core parameter set of the battery cover;

[0019] in, Represents the core parameter set of the battery cover, Representative The time value of the time period, Representative The maximum value of pressure within the fluctuation range, Representative The minimum pressure within the fluctuation range, Representative The fluctuation trend difference of the time period, Represents the number of time intervals.

[0020] As a further solution of the present invention, the step of obtaining the nonlinear parameter mapping coefficient of the battery cover is specifically as follows:

[0021] Based on the temperature variation range and pressure variation range in the battery cover core parameter set, the hysteresis coefficient and dynamic offset of each fluctuation trend interval are calculated, the fluctuation trend and data offset are analyzed, and a preliminary nonlinear parameter evaluation set is generated by reducing the fluctuation range;

[0022] Utilizing the preliminary nonlinear parameter evaluation set, calculating the hysteresis and feedback between the reduction parameter groups, and establishing a parameter relationship mapping by comparing the reduction strengths of hysteresis and feedback and combining the matching degree between the nonlinear coefficient and the change trend;

[0023] The result of the parameter relationship mapping is obtained by using the formula:

[0024] ;

[0025] The contribution of each mapping coefficient is integrated to generate the battery cover nonlinear parameter mapping coefficient;

[0026] in, represents the nonlinear parameter mapping coefficient of the battery cover, Representative The influence weight of each parameter group, represents the adjustment factor of the hysteresis coefficient, Representative The pressure change of each parameter group, represents the adjustment factor of the feedback strength, represents the temperature change, Represents the number of parameter groups.

[0027] As a further solution of the present invention, the steps for obtaining the dynamic adjustment path coefficient of the battery cover are specifically as follows:

[0028] Based on the nonlinear parameter mapping coefficient of the battery cover, the real-time temperature change rate and pressure change rate are extracted, the correlation between the temperature change trend and the pressure change trend is analyzed, and a preliminary trend adjustment analysis set is generated through interactive calculation of the trend data of the two;

[0029] Utilizing the preliminary trend adjustment analysis set, analyzing the offset relationship between the temperature change trend and the pressure change trend, and establishing an offset analysis model by comparing the matching degree of multiple trends and combining corresponding adjustment parameters;

[0030] Through the above-mentioned offset analysis model, combined with the real-time adjustment trend and matching coefficient, the formula is adopted:

[0031] ;

[0032] Calculate the dynamic adjustment path of each data point and generate the dynamic adjustment path coefficient of the battery cover;

[0033] in, Represents the dynamic adjustment path coefficient of the battery cover, Representative The adjusted weights of the data points, represents the adjustment factor of the matching coefficient, represents the rate of temperature change, represents the sensitivity factor for trend adjustment, represents the rate of change of pressure, Represents the total number of data points.

[0034] As a further solution of the present invention, the step of obtaining the battery cover parameter feedback rate distribution value is specifically as follows:

[0035] Based on the dynamic adjustment path coefficient of the battery cover, the real-time temperature, pressure and time values ​​of the vulcanization stage are extracted, the difference between the current temperature value and the target temperature in the real-time data is analyzed, and dynamic data sampling is performed by comparing the deviation characteristics and the time span to generate a real-time monitoring data set;

[0036] Using the real-time monitoring data set, the current instantaneous temperature and pressure offsets are calculated by combining the parameter mapping relationship between pressure value and time value, and an instantaneous offset analysis model is established by calculating the variation range of the offsets in different time periods;

[0037] By using the instantaneous offset analysis model, combined with the feedback rate and pressure-time relationship, the formula is adopted:

[0038] ;

[0039] Calculate the feedback rate distribution trend and generate the battery cover parameter feedback rate distribution value;

[0040] in, Represents the distribution value of the battery cover parameter feedback rate, Representative The feedback rate of data points, Represents the pressure value, Represents a time value, Represents the adjustment coefficient, which is used to adjust the intensity of the impact of pressure and time. Represents the total number of data points.

[0041] As a further solution of the present invention, the steps for obtaining the multi-objective optimization adjustment value of the battery cover are specifically as follows:

[0042] Based on the battery cover parameter feedback rate distribution value and the battery cover dynamic adjustment path coefficient, the efficiency target value and quality target value of the vulcanization stage are extracted. By comparing the distribution trend of the deviation range of the efficiency value and the quality value, and combining the real-time monitoring data to analyze the current target deviation characteristics, a real-time efficiency and quality deviation data set is generated;

[0043] Using the real-time efficiency and quality deviation data set, the correlation between the target deviation value and the feedback rate distribution trend is analyzed. By combining the interactive characteristics of the deviation range and trend changes, the dynamic distribution trend within the deviation range is calculated, and a joint analysis model of target deviation and feedback rate is established.

[0044] Through the target deviation and feedback rate joint analysis model, combined with the dynamic deviation trend and feedback rate value, the formula is adopted:

[0045] ;

[0046] Calculate dynamic deviation distribution and generate multi-objective optimization adjustment values ​​for the battery cover;

[0047] in, Represents the multi-objective optimization adjustment value of the battery cover, Representative The quality target weight of each data point, represents the deviation value, Representative The feedback rate distribution value of data points, 、 Represent the adjustment coefficients for deviation sensitivity and time sensitivity, Represents a time value, Represents the total number of data points.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are:

[0049] In this invention, by real-time acquisition and analysis of changes in temperature, pressure, and time during the vulcanization process, a core parameter set is extracted, abnormal data is accurately screened, and a nonlinear correlation map is constructed to achieve in-depth optimization of parameter hysteresis and dynamic feedback. By combining dynamic adjustment paths and real-time feedback trends, temperature and pressure matching is effectively controlled to ensure the precise connection between vulcanization conditions and process flows. By analyzing adjustment trends and parameter sums, the dynamic optimization path significantly reduces the deviation range during the production process, improving process consistency and quality stability. Multi-objective joint optimization further balances efficiency and quality, optimizes resource utilization, and reduces the impact of production fluctuations on product performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a system flow chart of the present invention;

[0051] Figure 2 Flowchart of the steps for obtaining the core parameter set of the battery cover of the present invention;

[0052] Figure 3 Flowchart of the steps for obtaining the nonlinear parameter mapping coefficients of the battery cover of the present invention;

[0053] Figure 4 A flow chart of the steps for obtaining the dynamic adjustment path coefficient of the battery cover of the present invention;

[0054] Figure 5 Flowchart of the steps for obtaining the distribution value of the battery cover parameter feedback rate of the present invention;

[0055] Figure 6 This is a flow chart of the steps for obtaining the multi-objective optimization adjustment value of the battery cover of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0057] 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," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0058] Example 1

[0059] See also Figure 1 , an intelligent battery cover loading and unloading and vulcanization control system includes:

[0060] The parameter extraction module extracts fluctuation interval data based on the temperature, pressure, and curing time values ​​of the battery cover collected during the curing process. It filters out abnormal values ​​within the offset range and calculates the fluctuation trend interval based on the time value to obtain the core parameter set of the battery cover.

[0061] The nonlinear modeling module calculates the hysteresis and feedback between parameter groups based on the temperature variation range, pressure variation range, and fluctuation trend interval in the core parameter set of the battery cover, extracts the hysteresis coefficient and dynamic offset, and generates the battery cover nonlinear parameter mapping coefficient by calculating the nonlinear coefficient and variation trend.

[0062] The optimal path adjustment module extracts the adjustment trend values ​​of the real-time temperature change rate and pressure change rate based on the nonlinear parameter mapping coefficient of the battery cover, analyzes the offset relationship between the temperature change trend and the pressure, calculates the parameter combination of the adjustment trend and the matching coefficient, and generates the dynamic adjustment path coefficient of the battery cover;

[0063] The real-time feedback module dynamically adjusts the path coefficient based on the battery cover, extracts the real-time temperature, pressure, and time values ​​during the vulcanization phase, calculates the difference between the current temperature deviation and the target temperature, calculates the instantaneous parameter offset based on the pressure and time values, analyzes the feedback rate distribution trend, and generates the battery cover parameter feedback rate distribution value;

[0064] The multi-objective optimization module extracts the deviation range of the efficiency target value and the quality target value based on the battery cover parameter feedback rate distribution value and the battery cover dynamic adjustment path coefficient, analyzes the target deviation value and the feedback rate distribution trend, analyzes the dynamic deviation distribution through joint trend value, and generates the battery cover multi-objective optimization adjustment value.

[0065] The battery cover core parameter set includes a temperature change range, a pressure change range, and a fluctuation trend interval. The battery cover nonlinear parameter mapping coefficient includes a lag coefficient, a dynamic offset, and a nonlinear coefficient. The battery cover dynamic adjustment path coefficient includes a real-time temperature change rate adjustment trend value, a real-time pressure change rate adjustment trend value, and a parameter combined value. The battery cover parameter feedback rate distribution value includes a current temperature deviation, a target temperature difference value, and an instantaneous parameter offset. The battery cover multi-objective optimization adjustment value includes an efficiency target value deviation range, a quality target value deviation range, and a dynamic deviation distribution.

[0066] Please refer to Figure 2 The acquisition steps of the battery cover core parameter set are as follows:

[0067] The temperature value and the pressure value of the battery cover are extracted from the vulcanization process. According to the vulcanization time, the sampling paragraphs are differentiated, the temperature and pressure changes in the time range are calculated, the temperature fluctuation range and the pressure fluctuation range in each time period are selected, and the initial temperature fluctuation data set and the pressure fluctuation data set are established.

[0068] The sampling interval is divided into several paragraphs based on the vulcanization time. For each sampling data of temperature and pressure value, the temperature fluctuation and pressure fluctuation in each interval are calculated according to the predefined time interval. The difference between the maximum value and the minimum value in the interval is calculated by the temperature data and the pressure data in the time interval, so as to quantify the fluctuation amplitude in each interval. The obtained fluctuation amplitude is compared with the preset threshold value, and the effective fluctuation paragraph that does not exceed the threshold value is selected through logical judgment. The data points that do not meet the conditions are removed, and the data of the selected effective fluctuation paragraph are stored in the temperature fluctuation data set and the pressure fluctuation data set respectively as the initial fluctuation data set.

[0069] The difference between the maximum value and the minimum value of the multi-fluctuation interval is calculated using the initial temperature fluctuation data set and the pressure fluctuation data set. The data that exceeds the range is selected by comparing the difference value with the set offset threshold value, and the abnormal values outside the offset range are removed to generate the selected fluctuation interval data set.

[0070] The difference between the maximum value and the minimum value is calculated by the point-by-point comparison method, and the fluctuation amplitude in each fluctuation interval is calculated. Whether these amplitude values exceed the defined offset threshold is judged in turn. For the interval data exceeding the offset range, all the corresponding record points are removed. For the data meeting the offset range condition, it is reclassified into the screening result. For the screened fluctuation data set, the fluctuation interval data set is sorted according to the fluctuation amplitude again, and the screened fluctuation interval data set is obtained.

[0071] From the screened fluctuation interval data set, the fluctuation trend corresponding to each time value is calculated, and the trend weight is determined by combining the fluctuation trend and the time weight. The formula is:

[0072] ;

[0073] The battery cover core parameter set is obtained.

[0074] Among them, represents the battery cover core parameter set, represents the time value of the first time period, represents the maximum value of the pressure in the first fluctuation interval, represents the minimum value of the pressure in the first fluctuation interval, represents the fluctuation trend difference value of the first time period, represents the number of time intervals.

[0075] The formula is:

[0076] ;

[0077] The beneficial effect of the formula is that by comparing the difference between the maximum value and the minimum value in the fluctuation interval with the time weight and the fluctuation trend, the contribution of the fluctuation change to the core parameter set is refined, and the accuracy and refinement degree of parameter extraction are improved.

[0078] Formula details and formula calculation derivation process:

[0079] Suppose that the number of time periods obtained from the screened fluctuation interval data set is , the time value is , the maximum value of the pressure in the fluctuation interval is , the minimum value of the pressure is , and the fluctuation trend difference value is . The formula is:

[0080] ;

[0081] ;

[0082] ;

[0083] ;

[0084] The results show that the core parameter set value after weighted calculation is 1.713, reflecting the relative quantitative value of the comprehensive evaluation of data in each fluctuation range. This result will be used to further verify and optimize the ability to extract core parameters from fluctuation trends.

[0085] See also Figure 3 , the specific steps for obtaining the nonlinear parameter mapping coefficient of the battery cover are:

[0086] Based on the temperature and pressure variation ranges in the battery cover core parameter set, the hysteresis coefficient and dynamic offset of each fluctuation trend interval are calculated, the fluctuation trend and data offset are analyzed, and a preliminary nonlinear parameter evaluation set is generated by reducing the fluctuation range.

[0087] By screening the fluctuation amplitude difference in the temperature variation range and the increment of the pressure variation range, the screened parameters are input into the hysteresis calculation formula: ,in Represents the fluctuation increment in the pressure variation range, Represents the fluctuation increment of the corresponding temperature change range. The hysteresis calculation result is used as the input parameter. Combined with the time value in the core parameter set, the dynamic offset calculation is performed. The dynamic offset formula is: ,in, is the time value, the calculated hysteresis coefficient With dynamic offset They are all stored in a nonlinear parameter set and cross-checked with the fluctuation trend interval value. Outliers are removed by gradually adjusting the calculation threshold. The outlier screening standard is based on whether the difference between adjacent values ​​of each fluctuation trend exceeds the preset range to obtain a preliminary nonlinear parameter evaluation set.

[0088] Using the preliminary nonlinear parameter evaluation set, the hysteresis and feedback between the reduction parameter groups are calculated. By comparing the reduction strength of hysteresis and feedback, combined with the matching degree of nonlinear coefficient and change trend, the parameter relationship mapping is established.

[0089] When calculating the hysteresis, the mean and standard deviation of all hysteresis coefficients are calculated, and the hysteresis coefficients with large deviations are recalculated. The recalculation is corrected by adjusting the calculation formula of the fluctuation trend range. The correction formula is: ,in is the adjustment coefficient, which is determined based on the mean fluctuation range of adjacent fluctuation intervals. After adjustment, the hysteresis parameter is recalculated. The feedback is calculated by calculating the correlation coefficient between the fluctuation range of the dynamic offset and the hysteresis parameter. The correlation coefficient formula is: ,in and are the means of hysteresis and dynamic offset respectively. The feedback parameter value is determined by the size of the correlation coefficient, and the parameter relationship mapping is established by combining hysteresis and feedback.

[0090] Map the results through parameter relationships using the formula:

[0091] ;

[0092] The contribution of each mapping coefficient is integrated to generate the battery cover nonlinear parameter mapping coefficient;

[0093] in, represents the nonlinear parameter mapping coefficient of the battery cover, Representative The influence weight of each parameter group, represents the adjustment factor of the hysteresis coefficient, Representative The pressure change of each parameter group, represents the adjustment factor of the feedback strength, represents the temperature change, Represents the number of parameter groups.

[0094] formula:

[0095] ;

[0096] The benefit of the formula is that it introduces the weight parameter through the comprehensive calculation of hysteresis and dynamic offset and adjustment coefficient and , effectively optimizing the accuracy and granularity of the mapping coefficients.

[0097] Detailed explanation of the formula and the process of formula calculation and derivation:

[0098] ;

[0099] Calculate each term:

[0100] Item 1:

[0101] ;

[0102] Item 2:

[0103] ;

[0104] Item 3:

[0105] ;

[0106] Sum:

[0107] ;

[0108] The results show that the value of the nonlinear parameter mapping coefficient of the battery cover is 111.176, indicating that the nonlinear relationship between hysteresis, dynamic offset and fluctuation trend is accurately quantified, which can be used to further evaluate the impact of the vulcanization process on the performance of the battery cover.

[0109] See also Figure 4 ,The specific steps for obtaining the dynamic adjustment path coefficient of the battery cover are:

[0110] Based on the nonlinear parameter mapping coefficients of the battery cover, the real-time temperature change rate and pressure change rate are extracted, and the correlation between the temperature change trend and the pressure change trend is analyzed. Through the interactive calculation of the trend data of the two, a preliminary trend adjustment analysis set is generated;

[0111] By monitoring the temperature and pressure changes of the battery cover every minute during the vulcanization process, the change rates of the two are calculated respectively, and divided according to the time period of the sampling points to form a trend sequence. Using the comparative analysis method, the temperature change rate and the pressure change rate are converted into a trend ratio according to the ratio of adjacent time points. By eliminating the abnormal points with discontinuous jumps in the trend ratio, the continuously changing interval is screened. Then, the average change rate is calculated according to the screened trend ratio, and the dynamic adjustment value of the trend change rate is calculated. By performing weighted calculation on the continuous adjustment values ​​of the trend change rate, a preliminary trend association between the temperature and pressure change rates is established, and finally a preliminary trend adjustment analysis set is generated.

[0112] Using the preliminary trend adjustment analysis set, the offset relationship between the temperature change trend and the pressure change trend is analyzed. By comparing the matching degree of multiple trends and combining the corresponding adjustment parameters, an offset analysis model is established;

[0113] The offset between the temperature change rate and the pressure change rate is calculated by the following formula: ,in, is the temperature change rate, For the pressure change rate, each group of offset values ​​is calculated to generate an offset value sequence. The offset value sequence is filtered by setting an offset threshold. The data points below the offset threshold are retained and the mean of their distribution is calculated. The mean is matched with the trend change rate in the time series to reduce the change trend of the offset value. The matched offset trend value is integrated into the offset analysis model to establish the offset analysis model.

[0114] Through the offset analysis model, combined with the real-time adjustment trend and matching coefficient, the formula is adopted:

[0115] ;

[0116] Calculate the dynamic adjustment path of each data point and generate the dynamic adjustment path coefficient of the battery cover;

[0117] in, Represents the dynamic adjustment path coefficient of the battery cover, Representative The adjusted weights of the data points, represents the adjustment factor of the matching coefficient, represents the rate of temperature change, represents the sensitivity factor for trend adjustment, represents the rate of change of pressure, Represents the total number of data points.

[0118] formula:

[0119] ;

[0120] The benefit of the formula is that, by combining the matching coefficient with the exponent of the dynamic rate of change and the denominator adjustment factor, it can effectively evaluate the complex interactive relationship between the dynamic adjustment of temperature and pressure, and improve the accurate description of the dynamic adjustment path.

[0121] Detailed explanation of the formula and the process of formula calculation and derivation:

[0122] set up , , , , , , enter the formula to calculate:

[0123] ;

[0124] Calculate the numerator:

[0125] ;

[0126] Calculate the denominator:

[0127] ;

[0128] Divide the numerator by the denominator:

[0129] ;

[0130] The final result is:

[0131] ;

[0132] The results show that the value of the dynamic adjustment path coefficient of the battery cover is 7.565. The matching and adjustment values ​​after reduction reflect the overall trend relationship of the interactive adjustment of temperature and pressure, and generate the dynamic adjustment path coefficient of the battery cover.

[0133] See also Figure 5 ,The specific steps for obtaining the distribution value of the battery cover parameter feedback rate are:

[0134] Based on the dynamic adjustment path coefficient of the battery cover, the real-time temperature, pressure and time values ​​of the vulcanization stage are extracted. The difference between the current temperature value and the target temperature in the real-time data is analyzed. Dynamic data sampling is performed by comparing the deviation characteristics and time span to generate a real-time monitoring data set.

[0135] First, the real-time temperature data is segmented according to the timestamp and the average value and variance of each time period are marked. By monitoring the real-time pressure value, the pressure values ​​with abnormal fluctuation range are screened out. At the same time, the time interval of adjacent time periods is calculated based on the time value. Then, the difference between the real-time temperature value and the target temperature range is compared and the deviation distribution is recorded. The fluctuation characteristics of the current temperature are determined based on the peak value and variance of the deviation distribution. The above data are used to generate a real-time monitoring data set containing real-time temperature values, pressure values ​​and deviation characteristics.

[0136] Using real-time monitoring data sets, the current instantaneous temperature and pressure offsets are calculated by combining the parameter mapping relationship between pressure values ​​and time values. By calculating the variation range of the offsets in different time periods, an instantaneous offset analysis model is established.

[0137] Firstly, the pressure values ​​in the monitoring data set are divided into different intervals and the time distribution density of each interval is calculated. The areas with significant pressure changes are screened out according to the time value distribution characteristics. Then, the instantaneous temperature offset in different pressure intervals is calculated in combination with the temperature deviation characteristics. The instantaneous offset is interactively mapped with the time value of each time period. The trend curves of instantaneous temperature and pressure offset are calculated through the time series change model, and an instantaneous offset analysis model is established.

[0138] Through the instantaneous offset analysis model, combined with the feedback rate and pressure-time relationship, the formula is adopted:

[0139] ;

[0140] Calculate the feedback rate distribution trend and generate the battery cover parameter feedback rate distribution value;

[0141] in, Represents the distribution value of the battery cover parameter feedback rate, Representative The feedback rate of data points, Represents the pressure value, Represents a time value, Represents the adjustment coefficient, which is used to adjust the intensity of the impact of pressure and time. Represents the total number of data points.

[0142] formula:

[0143] ;

[0144] The formula is beneficial in that, by introducing an adjustment factor for the feedback rate and the nonlinear relationship between pressure and time, it can effectively capture the dynamic changes of parameters, especially in the case of asymmetric fluctuations or rapid changes in a short period of time, improving calculation accuracy and adaptability.

[0145] Detailed explanation of the formula and the process of formula calculation and derivation:

[0146] , set the pressure value , time value , feedback rate , adjustment coefficient ;

[0147] First calculate the offset value of each item :

[0148] ;

[0149] Then calculate :

[0150] ;

[0151] Then calculate the denominator :

[0152] ;

[0153] Final calculation The weighted sum of:

[0154] ;

[0155] The results show that the calculation of the feedback rate distribution value integrates the relationship between pressure, time and feedback rate. This indicates that the feedback rate in this stage has achieved a high consistency in nonlinear changes, and can be further used to describe the dynamic adjustment state of parameters in the vulcanization process.

[0156] See also Figure 6 The specific steps for obtaining the multi-objective optimization adjustment value of the battery cover are as follows:

[0157] Based on the battery cover parameter feedback rate distribution value and the battery cover dynamic adjustment path coefficient, the efficiency target value and the quality target value in the vulcanization stage are extracted, the distribution trend of the deviation range of the efficiency value and the quality value is compared, the current target deviation characteristics are analyzed combined with the real-time monitoring data, and the real-time efficiency and quality deviation data set is generated;

[0158] By analyzing the deviation range of the efficiency target value and the quality target value in the vulcanization stage, the real-time monitoring data of the efficiency target value and the quality target value in the vulcanization stage is extracted respectively, including real-time efficiency value, actual output quantity and real-time pressure and temperature value, a real-time deviation analysis model based on data acquisition is established, the target value is compared with the actual value item by item, and the deviation percentage formula The deviation range is calculated, then the trend between the efficiency target value deviation and the quality target value deviation is compared and analyzed, the correlation between pressure and temperature fluctuation and deviation value is calculated combined with the dynamic change of real-time pressure value and temperature value, the fluctuation coefficient formula The influence of pressure and temperature fluctuation on efficiency and quality target is calculated, and finally the real-time efficiency and quality deviation data set is generated by monitoring the deviation range distribution trend and the data sampling model, integrating the correlation analysis of target value and feedback rate.

[0159] Using the real-time efficiency and quality deviation data set, the correlation between target deviation value and feedback rate distribution trend is analyzed, the dynamic distribution trend in the deviation range is calculated combined with the interactive characteristics of deviation range and trend change, and the target deviation and feedback rate joint analysis model is established;

[0160] The correlation between target deviation value and feedback rate distribution trend is analyzed, first the dynamic change value of each feedback rate in the feedback rate distribution trend and the associated time point are extracted, and the relationship matrix between target deviation value and feedback rate trend is constructed combined with the fluctuation coefficient in efficiency and quality deviation, and the collaborative change rate formula The degree of cooperation between the two is obtained, and further through the sensitivity analysis of adjusting the fluctuation coefficient, the change trend of the deviation value is fitted by using the distribution characteristics, the dynamic distribution trend in the fluctuation characteristic range is calculated, and the target deviation and feedback rate joint analysis model is established combined with the regional stability and fluctuation amplitude of the feedback rate trend.

[0161] Through the target deviation and feedback rate joint analysis model, combined with the dynamic deviation trend and the feedback rate value, the formula is used:

[0162] ;

[0163] Calculate the dynamic deviation distribution to generate the multi-objective optimization adjustment value of the battery cover;

[0164] Among them, a battery cover multi-objective optimization adjustment value, a quality target weight representing the th data point, a deviation value, a feedback rate distribution value representing the th data point, 、 an adjustment coefficient representing the adjustment sensitivity of the deviation and the time sensitivity, respectively, a time value, a total number of data points.

[0165] Formula:

[0166] ;

[0167] The advantage of the formula is that by introducing the exponential adjustment of the deviation value and the feedback rate distribution value, combined with the time sensitivity adjustment coefficient and the deviation sensitivity adjustment coefficient , the dynamic correlation of the deviation value and the feedback rate distribution can be accurately controlled, and the real-time adjustment ability of the deviation distribution is optimized.

[0168] Formula details and formula calculation derivation process:

[0169] calculated by the quality target and the actual achievement rate, calculated by the difference between the efficiency target value and the real-time monitoring value, calculated by the feedback rate distribution trend analysis, set according to the adjustment requirement of the deviation sensitivity, set according to the influence of time on deviation adjustment, calculated by time monitoring data;

[0170] Substitute into the formula:

[0171] ;

[0172] The results show that the battery cover multi-objective optimization adjustment value is 0.45, which represents the comprehensive optimization ability level under the current deviation distribution and feedback rate conditions, and can be used to further guide the dynamic adjustment distribution.

[0173] The above is only a preferred embodiment of the present application, and is not intended to limit the present application in other forms. Any skilled person in the art can use the disclosed technical content to make changes or modifications to equivalent embodiments applied to other fields, but any simple modification, equivalent change and modification made according to the technical essence of the present application to the above embodiments shall still fall within the protection scope of the present application.

Claims

1. An intelligent battery cover loading and unloading and vulcanization control system, characterized in that: The system comprises: The parameter extraction module extracts fluctuation interval data based on the temperature, pressure, and curing time values ​​of the battery cover collected during the curing process. It filters out abnormal values ​​within the offset range and calculates the fluctuation trend interval based on the time value to obtain the core parameter set of the battery cover. The nonlinear modeling module calculates the hysteresis and feedback between parameter groups based on the temperature variation range, pressure variation range and fluctuation trend interval in the battery cover core parameter set, extracts the hysteresis coefficient and dynamic offset, and generates the battery cover nonlinear parameter mapping coefficient by calculating the nonlinear coefficient and variation trend; The optimal path adjustment module extracts the adjustment trend values ​​of the real-time temperature change rate and the pressure change rate based on the nonlinear parameter mapping coefficient of the battery cover, analyzes the offset relationship between the temperature change trend and the pressure, calculates the parameter combination of the adjustment trend and the matching coefficient, and generates the dynamic adjustment path coefficient of the battery cover; The real-time feedback module dynamically adjusts the path coefficient of the battery cover, extracts the real-time temperature value, pressure value and time value of the vulcanization stage, calculates the difference between the current temperature deviation and the target temperature, calculates the instantaneous parameter offset based on the pressure and time values, analyzes the feedback rate distribution trend, and generates the battery cover parameter feedback rate distribution value; The multi-objective optimization module extracts the deviation range of the efficiency target value and the quality target value in the vulcanization stage based on the feedback rate distribution value of the battery cover parameters and the dynamic adjustment path coefficient of the battery cover, analyzes the target deviation value and the feedback rate distribution trend, analyzes the dynamic deviation distribution through the joint trend value, and generates the multi-objective optimization adjustment value of the battery cover.

2. The intelligent battery cover loading and unloading and vulcanization control system according to claim 1, characterized in that: The core parameter set of the battery cover includes the temperature change range, the pressure change range, and the fluctuation trend interval; the nonlinear parameter mapping coefficient of the battery cover includes the hysteresis coefficient, the dynamic offset, and the nonlinear coefficient; the dynamic adjustment path coefficient of the battery cover includes the real-time temperature change rate adjustment trend value, the real-time pressure change rate adjustment trend value, and the parameter sum value; the battery cover parameter feedback rate distribution value includes the current temperature deviation, the target temperature difference, and the instantaneous parameter offset; the battery cover multi-objective optimization adjustment value includes the efficiency target value deviation range, the quality target value deviation range, and the dynamic deviation distribution.

3. The intelligent battery cover loading and unloading and vulcanization control system according to claim 2, characterized in that: The steps for obtaining the battery cover core parameter set are specifically as follows: Extract the temperature and pressure values ​​of the battery cover during the vulcanization process, differentiate sampling segments according to the vulcanization time, calculate the temperature and pressure changes within the time range, filter the temperature and pressure fluctuation ranges in each time period, and establish the initial temperature and pressure fluctuation data sets; Using the initial temperature fluctuation data set and the pressure fluctuation data set, calculating the difference between the maximum and minimum values ​​of multiple fluctuation intervals, filtering out-of-range data based on the difference and comparing it with a set offset threshold, eliminating abnormal values ​​outside the offset range, and generating a filtered fluctuation interval data set; From the filtered fluctuation range data set, calculate the fluctuation trend corresponding to each time value, and determine the trend weight by combining the fluctuation trend with the time weight, using the formula: ； Get the core parameter set of the battery cover; in, Represents the core parameter set of the battery cover, Representative The time value of the time period, Representative The maximum value of pressure within the fluctuation range, Representative The minimum pressure within the fluctuation range, Representative The fluctuation trend difference of the time period, Represents the number of time intervals.

4. The intelligent battery cover loading and unloading and vulcanization control system according to claim 3, characterized in that: The steps for obtaining the nonlinear parameter mapping coefficient of the battery cover are specifically as follows: Based on the temperature variation range and pressure variation range in the battery cover core parameter set, the hysteresis coefficient and dynamic offset of each fluctuation trend interval are calculated, the fluctuation trend and data offset are analyzed, and a preliminary nonlinear parameter evaluation set is generated by reducing the fluctuation range; Utilizing the preliminary nonlinear parameter evaluation set, calculating the hysteresis and feedback between the reduction parameter groups, and establishing a parameter relationship mapping by comparing the reduction strengths of hysteresis and feedback and combining the matching degree between the nonlinear coefficient and the change trend; The result of the parameter relationship mapping is obtained by using the formula: ； The contribution of each mapping coefficient is integrated to generate the battery cover nonlinear parameter mapping coefficient; in, represents the nonlinear parameter mapping coefficient of the battery cover, Representative The influence weight of each parameter group, represents the adjustment factor of the hysteresis coefficient, Representative The pressure change of each parameter group, represents the adjustment factor of the feedback strength, represents the temperature change, Represents the number of parameter groups.

5. The intelligent battery cover loading and unloading and vulcanization control system according to claim 4, characterized in that: The steps for obtaining the dynamic adjustment path coefficient of the battery cover are specifically as follows: Based on the nonlinear parameter mapping coefficient of the battery cover, the real-time temperature change rate and pressure change rate are extracted, the correlation between the temperature change trend and the pressure change trend is analyzed, and a preliminary trend adjustment analysis set is generated through interactive calculation of the trend data of the two; Utilizing the preliminary trend adjustment analysis set, analyzing the offset relationship between the temperature change trend and the pressure change trend, and establishing an offset analysis model by comparing the matching degree of multiple trends and combining corresponding adjustment parameters; Through the above-mentioned offset analysis model, combined with the real-time adjustment trend and matching coefficient, the formula is adopted: ； Calculate the dynamic adjustment path of each data point and generate the dynamic adjustment path coefficient of the battery cover; in, Represents the dynamic adjustment path coefficient of the battery cover, Representative The adjusted weights of the data points, represents the adjustment factor of the matching coefficient, represents the rate of temperature change, represents the sensitivity factor for trend adjustment, represents the rate of change of pressure, Represents the total number of data points.

6. The intelligent battery cover loading and unloading and vulcanization control system according to claim 5, characterized in that: The steps for obtaining the distribution value of the battery cover parameter feedback rate are specifically as follows: Based on the dynamic adjustment path coefficient of the battery cover, the real-time temperature, pressure and time values ​​of the vulcanization stage are extracted, the difference between the current temperature value and the target temperature in the real-time data is analyzed, and dynamic data sampling is performed by comparing the deviation characteristics and the time span to generate a real-time monitoring data set; Using the real-time monitoring data set, the current instantaneous temperature and pressure offsets are calculated by combining the parameter mapping relationship between pressure value and time value, and an instantaneous offset analysis model is established by calculating the variation range of the offsets in different time periods; By using the instantaneous offset analysis model, combined with the feedback rate and pressure-time relationship, the formula is adopted: ； Calculate the feedback rate distribution trend and generate the battery cover parameter feedback rate distribution value; in, Represents the distribution value of the battery cover parameter feedback rate, Representative The feedback rate of data points, Represents the pressure value, Represents a time value, Represents the adjustment coefficient, which is used to adjust the intensity of the impact of pressure and time. Represents the total number of data points.

7. The intelligent battery cover loading and unloading and vulcanization control system according to claim 6, characterized in that: The steps for obtaining the multi-objective optimization adjustment value of the battery cover are specifically as follows: Based on the battery cover parameter feedback rate distribution value and the battery cover dynamic adjustment path coefficient, the efficiency target value and quality target value of the vulcanization stage are extracted. By comparing the distribution trend of the deviation range of the efficiency value and the quality value, and combining the real-time monitoring data to analyze the current target deviation characteristics, a real-time efficiency and quality deviation data set is generated; Using the real-time efficiency and quality deviation data set, the correlation between the target deviation value and the feedback rate distribution trend is analyzed. By combining the interactive characteristics of the deviation range and trend changes, the dynamic distribution trend within the deviation range is calculated, and a joint analysis model of target deviation and feedback rate is established. Through the target deviation and feedback rate joint analysis model, combined with the dynamic deviation trend and feedback rate value, the formula is adopted: ； Calculate dynamic deviation distribution and generate multi-objective optimization adjustment values ​​for the battery cover; in, Represents the multi-objective optimization adjustment value of the battery cover, Representative The quality target weight of each data point, represents the deviation value, Representative The feedback rate distribution value of data points, 、 Represent the adjustment coefficients for deviation sensitivity and time sensitivity, Represents a time value, Represents the total number of data points.

Images