Method and system for controlling the vulcanization molding process of rubber gaskets for automotive engines

Abstract

The application discloses a control method and system for vulcanization forming process of automobile engine rubber pad, and relates to the related field of material forming. The method comprises the following steps: if the current production line is in the state of interruption-restart, collecting the first forming state data set before interruption, the first forming control parameter set and the second forming state data set of interruption-restart; calculating the crosslinking degree distribution matrix according to the first and second forming state data sets; searching the similar sample set by combining the sample database; obtaining the first N similar second forming control parameter sets based on the similar second forming control parameter set and the vulcanization forming quality index; performing parameter expansion to obtain N groups of candidate second forming control parameter sets, and performing optimization to generate the second forming control parameter set; and performing vulcanization forming control on the production line. The application solves the problems that the existing vulcanization forming control cannot compensate for the interruption influence and is prone to forming quality defects, and achieves the effects of compensating for the interruption influence of the production line and reducing forming quality defects.

Description

Technical Field

[0001] This application relates to the field of material forming, and in particular to a method and system for controlling the vulcanization process of automotive engine rubber pads. Background Technology

[0002] The vulcanization quality of automotive engine rubber gaskets directly determines their vibration damping and sealing performance, thus affecting engine operating stability, noise control, and service life, and has a crucial impact on the overall reliability of the vehicle. Currently, the mainstream technology in the industry for controlling the vulcanization process of rubber gaskets is closed-loop control based on preset fixed process parameters. This involves deploying temperature and pressure sensors to collect molding status data in real time, comparing it with preset standard process parameters, and using a PID control algorithm to provide feedback control to the heating and pressurizing mechanisms, ensuring that the vulcanization process parameters remain stable within the preset range. However, the control logic of existing methods relies on preset fixed process parameters and does not consider the impact of thermal history changes caused by sudden interruptions during the vulcanization process. When the production line is interrupted, the temperature decay and stagnation of the crosslinking reaction during the interruption can lead to uneven vulcanization quality after restarting, resulting in insufficient crosslinking, hardness deviations, and appearance defects, failing to effectively compensate for the molding quality after the interruption.

[0003] At present, the control of the vulcanization molding process of automotive engine rubber pads has technical problems such as the inability to effectively compensate for the impact of interruption and the easy occurrence of molding quality defects. Summary of the Invention

[0004] This application provides a control method and system for the vulcanization molding process of automotive engine rubber pads. It employs techniques such as detecting whether the rubber pad vulcanization molding production line is in an interruption-restart state; if so, collecting the molding state before and after the interruption, as well as the control parameter dataset before the interruption, and calculating the crosslinking degree distribution matrix based on this data; searching for similar sample sets in conjunction with the interruption-restart sample database; selecting the top N similar control parameter sets that meet the molding quality standards; expanding multiple candidate control parameters; and optimizing them with the goal of maximizing molding quality to generate a new set of molding control parameters that can compensate for the impact of interrupted thermal history. Based on this new parameter set, the vulcanization molding process of the production line is controlled. These techniques solve the technical problems of existing automotive engine rubber pad vulcanization molding process control, such as the inability to effectively compensate for the impact of interruptions and the susceptibility to molding quality defects. The system effectively compensates for the impact of production line interruptions, reduces molding quality defects, and ensures stable vulcanization molding quality.

[0005] This application provides a control method for the vulcanization molding process of automotive engine rubber gaskets, comprising: detecting whether the current rubber gasket vulcanization molding production line is in an interruption-restart state; if in an interruption-restart state, collecting interruption-restart data from the timing window before the interruption, including a first molding state dataset, a first molding control parameter set, and a second molding state dataset from the interruption-restart timing window; calculating a crosslinking degree distribution matrix based on the first molding state dataset and the second molding state dataset; searching the interruption-restart sample database to obtain a set of similar samples corresponding to the crosslinking degree distribution matrix; obtaining the top N similar second molding control parameter sets whose vulcanization molding quality indicators are greater than a preset threshold based on the similar second molding control parameter sets corresponding to the similar sample sets and the corresponding vulcanization molding quality indicators; expanding candidate control parameters based on the N similar second molding control parameter sets to obtain N sets of candidate second molding control parameter sets, optimizing the N sets of candidate second molding control parameter sets with maximizing the vulcanization molding quality indicators as the optimization objective, and generating a second molding control parameter set for compensating for the historical effects of interruption heat; and controlling the vulcanization molding of the current rubber gasket vulcanization molding production line according to the second molding control parameter set.

[0006] In a possible implementation, the following processing is performed: an interruption-restart sample database is constructed, which includes a first molding state data sample set, a first molding control parameter sample set, a second molding state data sample set, a second molding control parameter sample set, and labels characterizing vulcanization molding quality based on interruption-restart event samples; wherein, the first molding control parameter sample set consists of the pre-interruption vulcanization molding control parameters of the rubber pad corresponding to the first molding state data sample set, and the second molding control parameter sample set consists of the post-interruption restart vulcanization molding control parameters of the rubber pad corresponding to the second molding state data sample set.

[0007] In a possible implementation, based on the first molding state dataset and the second molding state dataset, a crosslinking degree distribution matrix is ​​calculated, and the following processing is performed: the rubber pad is divided into multiple local regions according to the molding thickness, each local region corresponding to a crosslinking degree sub-matrix unit; the cumulative vulcanization time before interruption for each of the multiple local regions is calculated based on the first molding state dataset, and the temperature decay curve during interruption for each of the multiple local regions is calculated based on the second molding state dataset; the equivalent vulcanization time is calculated based on the cumulative vulcanization time before interruption and the temperature decay curve during interruption; the crosslinking degree of each local region is calculated based on the equivalent vulcanization time and the local pressure index, generating a crosslinking degree distribution matrix.

[0008] In a possible implementation, the following process is performed: the temperature decay curve during the interruption is obtained by introducing an interruption temperature decay function, which is obtained by performing decay and degradation analysis on the first formed state dataset based on the obtained interruption cumulative timing window.

[0009] In a possible implementation, the optimization objective is to maximize the vulcanization molding quality index. This optimization is performed on the N sets of candidate second molding control parameters to generate a second molding control parameter set used to compensate for the impact of interrupted thermal history. The following processes are then performed: N candidate second molding control parameter sets are selected from the N sets; the crosslinking evolution quality prediction model is simultaneously calculated on the N candidate second molding control parameter sets, outputting N vulcanization molding quality indices; based on the N vulcanization molding quality indices, a gradient descent search is performed on the N sets of candidate second molding control parameter sets for the next iteration until the rate of change of the optimal molding vulcanization molding quality index in consecutive iterations is less than a preset threshold, at which point the second molding control parameter set is output; wherein, the second molding control parameter set includes at least a segmented heating curve, a segmented pressure recovery curve, and a compensation vulcanization time.

[0010] In a possible implementation, the cumulative vulcanization time before interruption for each of the plurality of local regions is calculated based on the first molding state dataset, and the following processing is performed: the first molding state dataset includes the mold temperature field distribution, the dielectric response of the rubber material, and the cavity pressure timing of the timing window before interruption; based on the first molding state dataset, the first temperature-time curve and the first pressure-time curve of each local region are extracted; by performing a reaction rate integral on the first temperature-time curve, and correcting the reaction rate integral based on the first pressure-time curve, the cumulative vulcanization time before interruption is obtained.

[0011] In a possible implementation, the temperature decay curve during the interruption period for each of the plurality of local regions is calculated based on the second molding state dataset, and the following processing is performed: the second molding state dataset includes the mold temperature field distribution, the dielectric response of the rubber material, and the cavity pressure timing during the interruption restart window; the second temperature-time curve for each local region interruption restart is obtained; the temperature field change trend of the first temperature-time curve and the second temperature-time curve is analyzed to establish the temperature decay curve during the interruption period for each local region.

[0012] In a possible implementation, a second molding control parameter set is generated to compensate for the impact of interrupted thermal history, and the following processing is also performed: obtaining the type of the interrupt-restart state, including short-term interruption, medium-term interruption, and long-term interruption; setting the number of segments of the second molding control parameter set according to the short-term interruption, medium-term interruption, and long-term interruption respectively, wherein the number of segments of the short-term interruption, medium-term interruption, and long-term interruption increases sequentially.

[0013] This application also provides a control system for the vulcanization molding process of automotive engine rubber gaskets, including: a status detection module for detecting whether the current rubber gasket vulcanization molding production line is in an interruption-restart state; a dataset acquisition module for acquiring interruption-restart data from the timing window before the interruption if in an interruption-restart state, including a first molding state dataset, a first molding control parameter set, and a second molding state dataset from the interruption-restart timing window; a crosslinking degree distribution matrix calculation module for calculating a crosslinking degree distribution matrix based on the first molding state dataset and the second molding state dataset; and a similar sample set retrieval module for searching in conjunction with the interruption-restart sample database to obtain a similar sample set corresponding to the crosslinking degree distribution matrix. The system comprises: a screening module, used to obtain the top N similar second molding control parameter sets whose vulcanization molding quality indicators are greater than a preset threshold, based on the similar second molding control parameter sets corresponding to the similar sample sets and the corresponding vulcanization molding quality indicators; a second molding control parameter set generation module, used to expand the candidate control parameters based on the N similar second molding control parameter sets to obtain N sets of candidate second molding control parameter sets, and to optimize the N sets of candidate second molding control parameter sets with the goal of maximizing the vulcanization molding quality indicators, thereby generating a second molding control parameter set to compensate for the historical impact of interrupted heat; and a vulcanization molding control module, used to perform vulcanization molding control on the current rubber pad vulcanization molding production line according to the second molding control parameter set.

[0014] The proposed control method and system for the vulcanization molding process of automotive engine rubber gaskets first detects whether the current rubber gasket vulcanization molding production line is in an interruption-restart state. If it is, the system collects interruption-restart data from the time window before the interruption, including a first molding state dataset, a first molding control parameter set, and a second molding state dataset from the interruption-restart time window. Then, based on the first and second molding state datasets, a crosslinking degree distribution matrix is ​​calculated. A search is then performed using the interruption-restart sample database to obtain a set of similar samples corresponding to the crosslinking degree distribution matrix. Based on the similar second molding control parameter sets corresponding to these sets and the corresponding vulcanization molding quality indicators, the top N similar second molding control parameter sets with vulcanization molding quality indicators greater than a preset threshold are obtained. Next, candidate control parameters are expanded based on these N similar second molding control parameter sets to obtain N sets of candidate second molding control parameter sets. Optimization is performed on these N sets of candidate second molding control parameter sets with the goal of maximizing the vulcanization molding quality indicator, generating a second molding control parameter set to compensate for the historical impact of interrupted thermal processes. Finally, the vulcanization molding of the current rubber gasket vulcanization molding production line is controlled according to the second molding control parameter set. Through the above process, the method and system proposed in this application achieve the technical effect of effectively compensating for the impact of production line interruptions, reducing molding quality defects, and ensuring stable vulcanization molding quality. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0016] Figure 1 This is a flowchart illustrating the control method for the vulcanization molding process of automotive engine rubber gaskets provided in an embodiment of this application.

[0017] Figure 2 This is a schematic diagram of the control system for the vulcanization molding process of automotive engine rubber pads provided in an embodiment of this application.

[0018] Figure labeling: State detection module 10, Data set acquisition module 20, Crosslinking degree distribution matrix calculation module 30, Similar sample set retrieval module 40, Screening module 50, Second molding control parameter set generation module 60, Vulcanization molding control module 70. Detailed Implementation

[0019] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0020] This application provides a method for controlling the vulcanization molding process of automotive engine rubber gaskets, such as... Figure 1 As shown, the method includes:

[0021] Step S100: Detect whether the current rubber pad vulcanization molding production line is in an interrupted-restart state.

[0022] Specifically, the production line's PLC control system collects core operating parameters and, combined with timing-based status judgment rules, identifies whether the production line is in an interruption-restart state. This involves capturing the continuous triggering logic of interruption and restart signals, excluding non-target states such as normal shutdowns and debugging shutdowns. In practice, the main controller of the production line presets interruption trigger thresholds and restart judgment conditions, and collects the production line's operating status signals in real time, including motor operating status, mold closure status, vulcanization temperature control signals, and rubber material feeding signals, while simultaneously recording the signal timing. When the aforementioned core operating signals are simultaneously interrupted, such as for a duration ≥ 0.5 seconds and a restart signal is detected within 10 seconds after the interruption ends, it is determined to be in an interruption-restart state.

[0023] For example, if a production line experiences a sudden power outage that interrupts all operating signals, and power is restored after 2 minutes, the PLC will detect the power restoration and the production line will automatically restart. In this case, by comparing the signal timing and duration before and after the interruption, it can be determined that the process is in an interruption-restart state. If the shutdown occurs after normal production has ended and there is no subsequent restart signal, it is determined to be in a non-interruption-restart state, and the subsequent steps will not be performed.

[0024] Step S200: If in the interrupt-restart state, collect the interrupt-restart data of the timing window before the interruption, including the first molding state dataset, the first molding control parameter set, and the second molding state dataset of the interrupt-restart timing window.

[0025] Specifically, the real-time data acquisition module based on the PLC control system, combined with preset timing window division rules, collects two types of core datasets before and after the interruption. During execution, timing window parameters are first preset; for example, the timing window before the interruption is set to 30 seconds before the interruption signal is triggered, which can be adjusted according to the rubber pad vulcanization molding cycle. The interruption restart timing window is set to 15 seconds after the restart signal is triggered, to capture changes in the molding state at the initial stage of restart. Through control modules and various sensors deployed on the production line, such as temperature sensors, pressure sensors, and dielectric response sensors, the first molding state dataset is collected, including the temperature of each area of ​​the mold, the dielectric response value of the rubber material, and the pressure inside the vulcanization chamber within the timing window before the interruption. The first molding control parameter set consists of the control parameters output by the PLC before the interruption, including the target temperature of the mold, the target pressure inside the chamber, the rubber material feed rate, and the vulcanization time setpoint. The acquisition method is to call the PLC's historical control parameter cache. The second molding state dataset consists of the temperature of each area of ​​the mold, the dielectric response value of the rubber material, and the pressure inside the vulcanization chamber within the timing window after restart. The acquisition frequency is consistent with that before the interruption, and the initial state parameters at the restart time are recorded synchronously.

[0026] Step S300: Calculate the crosslinking degree distribution matrix based on the first molding state dataset and the second molding state dataset.

[0027] Specifically, the rubber pad is divided into multiple local regions according to its molding thickness. The crosslinking degree calculation range for each region is determined. The equivalent vulcanization time is calculated using the cumulative vulcanization time before interruption and the temperature decay curve during the interruption. Combined with local pressure indicators, the crosslinking degree calculation formula is used to calculate the crosslinking degree of each local region. Finally, these are integrated to form a crosslinking degree distribution matrix, reflecting the differences in crosslinking states in different regions of the rubber pad. In practice, the local regions are first divided, then the cumulative vulcanization time before interruption and the temperature decay curve are calculated, followed by the equivalent vulcanization time, and finally the crosslinking degree of each region is calculated and a matrix is ​​constructed.

[0028] Step S400: A search is performed using the interruption-restart sample database to obtain a set of similar samples corresponding to the crosslinking degree distribution matrix. Specifically, the interruption-restart sample database is constructed, comprising a first molding state data sample set, a first molding control parameter sample set, a second molding state data sample set, a second molding control parameter sample set, and labels characterizing vulcanization molding quality, all based on interruption-restart event samples. The first molding control parameter sample set consists of the pre-interruption vulcanization molding control parameters for the rubber pads corresponding to the first molding state data sample set, and the second molding control parameter sample set consists of the post-interruption-restart vulcanization molding control parameters for the rubber pads corresponding to the second molding state data sample set.

[0029] Specifically, an industrial database, such as MySQL Industrial Edition or InfluxDB, is used to build a sample database. Through data cleaning, labeling, and classification, various datasets of historical interruption-restart event samples are associated with quality labels to form a structured sample library for model training and similar sample retrieval. In practice, at least 1000 sets of historical interruption-restart event samples are collected. Each set includes a first molding state data sample set and a corresponding first molding control parameter sample set for the pre-interruption time series window, and a second molding state data sample set and a corresponding second molding control parameter sample set for the restart time series window. Quality inspection is performed on each set of samples to obtain labels characterizing the vulcanization molding quality. These quality labels use quantitative indicators, including rubber pad crosslinking degree, Shore hardness, tensile strength, and appearance defects. No defects are labeled 0, bubbles are labeled 1, cracks are labeled 2, and dimensional deviations are labeled 3. These quantitative indicators are integrated into the quality label for that sample. All sample data are cleaned, and outlier samples, such as those with a data missing rate ≥5% or quality labels exceeding the standard range by 30%, are removed. Numerical data, such as temperature, pressure, and dielectric response values, are standardized using the Z-score standardization method to eliminate the influence of dimensions. The cleaned samples are then categorized and stored in the database according to interruption type, such as short-term interruption, medium-term interruption, and long-term interruption. Each sample is assigned a unique sample ID, associated with various datasets and quality labels, and supports fuzzy retrieval based on forming status parameters.

[0030] For example, a sample ID is 20240501001, the interruption type is short interruption, the first molding state data sample set includes the average mold temperature of 155℃ and the average cavity pressure of 12MPa in the 30 seconds before the interruption, the first molding control parameter sample set is the mold target temperature of 155℃ and the pressure of 12MPa, the second molding state data sample set is the average mold temperature of 149℃ and the average cavity pressure of 11.6MPa in the 15 seconds after restart, the second molding control parameter sample set is the mold temperature of 152℃ and the pressure of 11.8MPa set after restart, the quality label is crosslinking degree of 90%, Shore hardness of 66D, tensile strength of 18MPa, and no defects in appearance (0). This sample is stored in the database according to the short interruption category, and can be retrieved by conditions such as mold temperature of 155℃±2℃ before interruption and short interruption.

[0031] A similarity retrieval algorithm, such as the Euclidean distance algorithm, is employed. Using the currently calculated crosslinking degree distribution matrix as the retrieval target, similarity calculations are performed between this matrix and the crosslinking degree distribution matrices of all samples in the interrupted-restart sample database. A similarity threshold is set, and samples meeting the similarity requirement are selected to form a similar sample set, ensuring a high degree of consistency between the retrieved samples and the current operating conditions. Specifically, the current crosslinking degree distribution matrix is ​​first converted into a vector form. Each sample in the sample database stores a corresponding crosslinking degree distribution vector. The Euclidean distance algorithm is used to calculate the similarity between the current vector and each sample vector; the smaller the Euclidean distance, the higher the similarity. A similarity threshold is set based on the sample distribution, and all samples with an Euclidean distance ≤ the similarity threshold are selected to form a similar sample set. If the number of similar samples is too large, they are sorted by Euclidean distance from smallest to largest, and the top 50 samples are selected as the similar sample set.

[0032] Step S500: Based on the similar second molding control parameter set corresponding to the similar sample set and the corresponding vulcanization molding quality index, obtain the top N similar second molding control parameter sets whose vulcanization molding quality index is greater than a preset threshold.

[0033] Specifically, based on industry standards and production requirements, preset thresholds for vulcanization molding quality indicators are set. For each sample in the similar sample set, its quality indicators are compared with the preset thresholds to select samples that meet the quality standards. Then, samples are sorted according to the quality indicators, and the second molding control parameter set corresponding to the top N samples is selected. This selects the control parameters for high-quality samples, providing a good foundation for expanding candidate parameters. In practice, firstly, preset thresholds for quality indicators are set, combined with the usage requirements of rubber pads. For example, crosslinking degree ≥85%, Shore hardness 60-70D, tensile strength ≥15MPa, and no defects in appearance (quality label 0). All four indicators must be met simultaneously to be considered as meeting the quality standards. Each sample in the similar sample set is traversed, and its vulcanization molding quality indicators and corresponding similar second molding control parameter sets are extracted. Each quality indicator is compared with the preset thresholds to select samples that meet all four indicators. For the compliant samples, they are sorted from high to low crosslinking degree. If the crosslinking degree is the same, they are sorted by tensile strength. If the tensile strength is still the same, they are sorted by Shore hardness. The value of N is set according to the number of samples and computational efficiency. For example, if N=10 is set, the similarity second shaping control parameter set corresponding to the top 10 samples is selected as the basis for candidate parameter expansion.

[0034] Step S600: Based on the N similar second molding control parameter sets, expand the candidate control parameters to obtain N sets of candidate second molding control parameter sets. With maximizing the vulcanization molding quality index as the optimization objective, optimize the N sets of candidate second molding control parameter sets to generate a second molding control parameter set for compensating for the impact of interrupted heat history.

[0035] Specifically, a parameter interpolation expansion method is used to expand N similar second molding control parameter sets, generating N candidate parameter sets. Each candidate parameter set contains multiple parameter combinations. The quality index of each parameter set is then predicted using a crosslinking evolution quality prediction model. An optimization algorithm is used to select the parameter combination with the best quality, which serves as the final second molding control parameter set. In other words, parameter expansion increases the optimization range, ensuring the optimal compensation parameters are found. In practice, the first step is candidate parameter expansion: interpolation expansion is performed on the core parameters of each similar second molding control parameter set. The expansion step size is set based on parameter sensitivity, ensuring that the expansion range of each parameter does not exceed the production allowable range. The expanded values ​​of each parameter are combined to form each candidate second molding control parameter set, with each similar parameter set corresponding to one candidate parameter set. The second step is parameter optimization: the N candidate parameter sets are sequentially input into the trained crosslinking evolution quality prediction model. The model outputs the vulcanization molding quality index corresponding to each parameter combination. A genetic algorithm is used for optimization to maximize the degree of crosslinking, tensile strength, optimize the Shore hardness to the optimal range, and eliminate appearance defects as the optimization objective. A fitness function is set by integrating the four quality indices; the higher the fitness value, the better the quality. The optimization process includes initializing the population, selection, crossover, and mutation. The number of iterations is set to 50, until the fitness value tends to stabilize, that is, the fitness value changes ≤0.01 for 5 consecutive iterations. The parameter combination with the highest fitness value is output, which is the second molding control parameter set used to compensate for the impact of interrupted thermal history.

[0036] Step S700: Perform vulcanization molding control on the current rubber pad vulcanization molding production line according to the second molding control parameter set.

[0037] Specifically, through the communication interface between the PLC control system and the crosslinking evolution quality prediction model, the second molding control parameter set generated by reverse optimization is transformed into control instructions executable by the PLC and sent to each actuator on the production line in real time. Simultaneously, the molding status is monitored in real time, and parameters are dynamically fine-tuned to ensure the stability of the vulcanization molding process. In specific execution, a communication connection is first established between the model and the PLC control system, using the Modbus TCP communication protocol to ensure data transmission delay ≤1 second. Parameters from the second molding control parameter set, such as the mold target temperature, cavity target pressure, compensated vulcanization time, and rubber material feeding speed, are transformed into digital control instructions for the PLC. For example, the temperature control instruction uses a PID control algorithm to convert the target temperature into a current signal to control the heating power of the heating element; the pressure control instruction is converted into the opening signal of the hydraulic valve to control the cavity pressure. Then, the control instructions are sent to each actuator on the production line in real time, including the mold heating system, hydraulic pressure control system, rubber material feeding system, and vulcanization time control system. During the vulcanization process, molding status data is collected in real time and compared with the target values ​​of the second molding control parameter set. If the deviation exceeds the allowable range, the control parameters are dynamically fine-tuned through the PLC's PID adjustment module. For example, if the mold temperature is detected to drop to 155℃ (target 156℃), the PLC issues a command to increase the heating power of the heating element to bring the temperature back to 156℃; if the pressure rises to 12.4MPa (target 12.2MPa), the hydraulic valve opening is reduced to bring the pressure back to 12.2MPa. Simultaneously, the compensation vulcanization time is precisely controlled by the PLC's timer, adding a compensation time to the normal vulcanization time after restarting to ensure full cross-linking of the rubber compound and compensate for the impact of interrupted heat history.

[0038] In one possible implementation, a crosslinking degree distribution matrix is ​​calculated based on the first molding state dataset and the second molding state dataset. Step S300 further includes step S310, which divides the rubber pad into multiple local regions according to the molding thickness, with each local region corresponding to a crosslinking degree sub-matrix unit. Specifically, based on the molding thickness of the rubber pad and combined with the temperature and pressure distribution characteristics during vulcanization, a uniform partitioning method is used to divide the local regions. Each region corresponds to an independent crosslinking degree calculation unit, forming a sub-matrix unit matching the number of regions. In specific execution, the molding thickness parameters of the rubber pad are first obtained according to the production drawings, and the partitioning interval is set. The partitioning interval can be adjusted according to the thickness, such as 1mm when the thickness is ≤10mm and 1.5mm when it is >10mm. Using the uniform partitioning method, multiple local regions are divided sequentially from the upper surface layer to the lower surface layer of the rubber pad, with the area of ​​each region being consistent with the cross-sectional area of ​​the rubber pad. A unique region number is assigned to each local region, such as region 1, region 2. Each region corresponds to a crosslinking degree sub-matrix unit, and the value of the sub-matrix unit is the crosslinking degree of that region. The dimension of the sub-matrix is ​​consistent with the number of regions. For example, the rubber pad is 10mm thick and divided into 10 local regions at 1mm intervals. Region 1 is the upper surface layer and region 10 is the lower surface layer. Each region corresponds to a crosslinking degree sub-matrix unit, which finally forms a 10×1 crosslinking degree distribution matrix. Each unit stores the crosslinking degree value of the corresponding region.

[0039] Step S320: Calculate the cumulative vulcanization time before interruption for each of the multiple local regions based on the first molding state dataset. Calculate the temperature decay curve during interruption for each of the multiple local regions based on the second molding state dataset. The temperature decay curve during interruption is obtained by introducing an interruption temperature decay function, which is obtained by performing decay and degradation analysis on the first molding state dataset based on the acquired interruption cumulative time sequence window. Specifically, an integral algorithm is used to calculate the cumulative vulcanization time before interruption for each local region. An interruption temperature decay function is constructed using a linear fitting algorithm. This function is used to calculate the temperature decay curve for each local region, providing a basis for calculating the equivalent vulcanization time. Specifically, the first part calculates the cumulative vulcanization time before interruption: extract the first temperature-time curve and the first pressure-time curve for each local region from the first molding state dataset, and calculate the cumulative vulcanization time using the integral form of the Arrhenius reaction rate equation. The second part constructs the interruption temperature decay function: The cumulative interruption time window, i.e., the duration from the interruption start time to the restart start time, is obtained. The final pre-interruption temperature of each local region is extracted from the first formed state dataset, and the initial restart temperature of each local region is extracted from the second formed state dataset. A linear fitting algorithm is used, with the interruption duration as the horizontal axis and temperature as the vertical axis, to fit the interruption temperature decay function. This function is obtained by performing attenuation degradation analysis on the temperature data in the first formed state dataset; that is, the accuracy of the linear fitting is verified by comparing the temperature decay patterns of multiple sets of historical interruption samples. The third part calculates the temperature decay curve: The interruption duration is divided into multiple time nodes. Each time node is substituted into the interruption temperature decay function to calculate the temperature value of each node. These temperature values ​​are arranged in chronological order to form the temperature decay curve during the interruption period of that local region.

[0040] Step S330: Calculate the equivalent vulcanization time according to the accumulated vulcanization time before the interruption and the temperature decay curve during the interruption. Specifically, the equivalent vulcanization time calculation formula combines the accumulated vulcanization time before the interruption with the temperature decay contribution during the interruption, and calculates the equivalent vulcanization time through integration. This transforms the non-standard vulcanization state during the interruption into an equivalent standard vulcanization time, ensuring the accuracy of the crosslinking degree calculation. In practice, the equivalent vulcanization time is calculated using a modified Arrhenius integral method. The reaction rate during the interruption is also calculated based on the temperature value in the temperature decay curve, consistent with the calculation standard for the reaction rate before the interruption. The integration interval is the entire interruption duration. The integral value is calculated using the trapezoidal integral method, that is, by calculating the average reaction rate of adjacent nodes through the reaction rate corresponding to each time node of the temperature decay curve, multiplying it by the time interval, and accumulating it to obtain the equivalent vulcanization contribution during the interruption. This is then added to the accumulated vulcanization time before the interruption to obtain the equivalent vulcanization time for each local region.

[0041] Step S340: Calculate the crosslinking degree of each local region based on the equivalent vulcanization time and local pressure index, generating a crosslinking degree distribution matrix. Specifically, using the crosslinking degree calculation formula, with the equivalent vulcanization time and local pressure index as input parameters, calculate the crosslinking degree of each local region. Then, arrange the crosslinking degrees of all regions in order of region number to form a crosslinking degree distribution matrix, reflecting the crosslinking uniformity of different regions. In specific execution, first determine the crosslinking degree calculation formula: Crosslinking degree = (equivalent vulcanization time / standard vulcanization time) × pressure influence coefficient × 100%, where the standard vulcanization time is the complete vulcanization time of the rubber pad under normal vulcanization without interruption. The pressure influence coefficient is calculated based on the average pressure of each local region. The local pressure index is extracted from the first molding state dataset and the second molding state dataset, taking the average pressure of the local region before interruption and after restart. The value range of the pressure influence coefficient is 0.9-1.1; the higher the pressure, the larger the coefficient. Specifically, 11 MPa corresponds to 0.95, 12 MPa corresponds to 1.0, and 13 MPa corresponds to 1.05. Intermediate pressures are calculated using linear interpolation. Then, the crosslinking degree of each local region is calculated by substituting the parameters. After the calculation is completed, the crosslinking degrees of all local regions are arranged in order of region number to form a crosslinking degree distribution matrix. The dimension of the matrix is ​​consistent with the division of local regions. If 10 local regions are divided, a 10×1 matrix is ​​formed, and each element corresponds to the crosslinking degree value of a region, reflecting the difference in crosslinking degree between different regions.

[0042] In one possible implementation, step S320 further includes step S321, where the first molding state dataset includes the mold temperature field distribution, rubber dielectric response, and cavity pressure timing of the timing window before interruption, calculated based on the first molding state dataset. Specifically, the mold temperature field distribution is collected by thermocouple temperature sensors deployed on and inside the mold surface. Three sensors are deployed in each of the upper, middle, and lower regions of the mold, for a total of nine sensors, to collect the temperature of each local region and integrate them into mold temperature field distribution data, including the temperature timing curve and average temperature of each local region. The rubber dielectric response is collected by a dielectric response sensor installed on the inner wall of the vulcanizing cavity, in direct contact with the rubber, to collect the dielectric constant of the rubber during the vulcanization process. The dielectric constant reflects the progress of the crosslinking reaction of the rubber; the higher the degree of crosslinking, the larger the dielectric constant, forming the rubber dielectric response timing data. The cavity pressure timing is collected by a pressure sensor installed at the inlet of the vulcanizing cavity, forming an cavity pressure timing curve, including the pressure fluctuation range and average pressure.

[0043] Step S322: Based on the first molding state dataset, extract the first temperature-time curve and the first pressure-time curve for each local region. Specifically, a data extraction algorithm is used to filter the temperature and pressure data corresponding to each local region from the first molding state dataset, sort them in chronological order, and form a time-series curve. In practice, firstly, mold temperature field distribution data is extracted from the first molding state dataset. Based on the number of each local region, temperature data collected by all temperature sensors in that region are filtered out. The arithmetic mean method is used to calculate the average temperature of that region at each time point. These average temperature values ​​are arranged in chronological order to form the first temperature-time curve for that local region, with time on the horizontal axis and temperature on the vertical axis. Simultaneously, cavity pressure time-series data is extracted from the first molding state dataset. Based on the division of local regions and the pressure field distribution pattern, the pressure sensor data corresponding to that region is used and arranged in chronological order to form the first pressure-time curve for each local region, with time on the horizontal axis and pressure on the vertical axis.

[0044] Step S323: By integrating the reaction rate on the first temperature-time curve and correcting the integrated reaction rate based on the first pressure-time curve, the cumulative vulcanization time before interruption is obtained. Specifically, the reaction rate corresponding to the first temperature-time curve is integrated using a numerical integration method to obtain the preliminary cumulative vulcanization time. Then, a pressure correction coefficient is calculated using the first pressure-time curve to correct the preliminary integration result, eliminating the influence of pressure fluctuations on the vulcanization reaction rate, and finally obtaining the accurate cumulative vulcanization time before interruption. In specific execution, the first step is to calculate the reaction rate: based on each temperature data point of the first temperature-time curve, the vulcanization reaction rate at the corresponding time point is calculated using the Arrhenius equation. Reaction rate = reaction rate constant × temperature correction coefficient, where the reaction rate constant is a fixed value set according to the rubber compound formulation. The temperature correction coefficient is positively correlated with temperature: 0.9 at 150℃, 1.0 at 155℃, and 1.1 at 160℃. Intermediate temperatures are calculated using linear interpolation. Each time point corresponds to a reaction rate value. The second step is reaction rate integration: The reaction rate is integrated using the trapezoidal integration method, with the integration interval being the time window before the interruption. The third step is pressure correction: The average pressure of each integration interval is extracted from the first pressure-time curve, and the corresponding pressure correction coefficient is calculated. The pressure correction coefficient ranges from 0.95 to 1.05, with 0.95 corresponding to 11 MPa, 1.0 to 12 MPa, and 1.05 to 13 MPa. Intermediate pressures are calculated using linear interpolation. The integral contribution of each integration interval is multiplied by the corresponding pressure correction coefficient, and then summed to obtain the final cumulative vulcanization time before the interruption.

[0045] In one possible implementation, the temperature decay curve during the interruption period corresponding to each of the plurality of local regions is calculated based on the second molding state dataset. Step S320 further includes step S324, whereby the second molding state dataset includes the mold temperature field distribution, the dielectric response of the rubber material, and the cavity pressure timing during the interruption restart timing window. Specifically, the parameters collected in the second molding state dataset are consistent with those in the first molding state dataset, and will not be elaborated here.

[0046] Step S325: Obtain the second temperature-time curve for each local region interrupted and restarted. Specifically, extract the mold temperature field distribution data from the second molding state dataset. Based on the number of each local region, filter the temperature data collected by all temperature sensors in that region. Calculate the average temperature of that region at each time point using the arithmetic mean method. Arrange these average temperature values ​​in chronological order to form the second temperature-time curve for that local region. The horizontal axis of the curve represents the time after restart, and the vertical axis represents the temperature. Extract the 0-second temperature value of this curve as the initial restart temperature for that local region, used for fitting the interrupted temperature decay curve.

[0047] Step S326: Analyze the temperature field change trends of the first temperature-time curve and the second temperature-time curve to establish a temperature decay curve for each local region during the interruption period. Specifically, by comparing the end temperature of the first temperature-time curve and the initial temperature of the second temperature-time curve, and combining the interruption duration, a curve fitting algorithm is used to fit the temperature decay curve during the interruption period. In specific execution, the first step is to extract key temperature data: extract the temperature value of the last time point from the first temperature-time curve, i.e., the temperature at the interruption trigger moment; extract the temperature value of the first time point from the second temperature-time curve, i.e., the temperature at the restart trigger moment. The second step is to obtain the interruption duration: record the timestamps of the interruption trigger moment and the restart trigger moment through the PLC control system, and calculate the difference between the two timestamps, which is the interruption duration. The third step is curve fitting: use a linear fitting algorithm, with the interruption duration as the horizontal axis and temperature as the vertical axis, to fit a linear temperature decay curve. During the fitting process, the least squares method is used to minimize the deviation between the fitted curve and the historical sample temperature decay data. The fourth step is to verify and optimize: retrieve historical samples from the interruption-restart sample database that are similar to the current interruption duration and temperature change range, extract the actual temperature decay data during the interruption, and compare it with the fitted temperature decay curve. If the deviation exceeds 1℃, polynomial fitting is used for correction to ensure the accuracy of the curve.

[0048] In one possible implementation, optimization is performed on the N sets of candidate second molding control parameters with the goal of maximizing the vulcanization molding quality index, generating a second molding control parameter set to compensate for the impact of interrupted heat history. Step S600 further includes step S610, selecting N candidate second molding control parameter sets from the N sets of candidate second molding control parameter sets respectively. Specifically, from the candidate parameter set expanded from each similar second molding control parameter set, one candidate parameter set is selected using random sampling or preferred sampling, for a total of N, consistent with the number of similar parameter sets, forming N candidate second molding control parameter sets to be optimized, providing a diversity basis for subsequent optimization. In specific execution, the value of N is first determined, and each similar second molding control parameter set corresponds to a set of candidate parameter sets. Using preferred sampling, the parameter combination with the smallest deviation from the original similar second molding control parameter set is selected from each set of candidate parameter sets, i.e., the original parameter combination itself. If the original parameter combination exceeds the production allowable range, the parameter combination with the smallest deviation and within the range is selected. To increase parameter diversity, a random sampling method can be used to randomly select one parameter combination from each set of candidate parameters.

[0049] Step S620: Simultaneously calculate the crosslinking evolution quality prediction model for the N candidate second molding control parameter sets, outputting N vulcanization molding quality indicators. Specifically, a parallel computing approach is adopted, combining the N candidate second molding control parameter sets with the current crosslinking evolution state vector and inputting them into the crosslinking evolution quality prediction model. The model calculates the quality indicators corresponding to each parameter set in parallel, outputting N quantified vulcanization molding quality indicators. In specific execution, the N candidate second molding control parameter sets are first standardized using the same standardization method as during model training. Then, each standardized candidate parameter set is concatenated with the currently constructed crosslinking evolution state vector to form the model input vector. Using GPU parallel computing technology, the N input vectors are simultaneously input into the trained CNN-LSTM hybrid model. Each input vector of the model corresponds to an output port, and the vulcanization molding quality indicators corresponding to each input vector are calculated in parallel, including crosslinking degree, Shore hardness, tensile strength, and appearance defects. After the calculation is completed, the output quality indicators are de-standardized and converted into quantitative values ​​for actual production, such as crosslinking degree of 85%-95% and Shore hardness of 60-70D. Each parameter set corresponds to a complete combination of quality indicators.

[0050] Step S630: Based on the N vulcanization molding quality indicators, perform gradient descent search from the N sets of candidate second molding control parameters for the next iteration until the rate of change of the optimal molding vulcanization molding quality indicator in consecutive iterations is less than a preset threshold. Output the second molding control parameter set, which includes at least a piecewise heating curve, a piecewise pressure recovery curve, and a compensated vulcanization time. Specifically, a small-batch gradient descent optimization algorithm is used, with the predicted quality indicators corresponding to the current N candidate parameter sets as feedback. The gradient value of each control parameter with respect to the quality indicators is calculated, and each candidate parameter is slightly adjusted according to the gradient direction to generate the N candidate parameter sets for the next iteration. During the iteration process, the optimal parameter combination for quality indicators is retained in each round, and the relative change rate of the optimal indicators for multiple consecutive rounds is calculated. When the change rate is less than a preset threshold, the iteration stops. The final output set of second molding control parameters is decomposed into segmented control instructions. For example, the temperature is divided into a rapid heating segment of 0-10 seconds after restart, a stable temperature segment of 10-30 seconds, and a compensation segment from 30 seconds until the end of vulcanization. The pressure is divided into a rapid pressure building segment, a pressure holding segment, and a micro-pressure compensation segment. The compensation vulcanization time is a fixed duration added on top of the original process time. The entire set of parameters is directly sent to the PLC for execution.

[0051] In one possible implementation, a second set of shaping control parameters is generated to compensate for the impact of interrupted thermal history. Step S600 further includes step S640, which obtains the type of the interrupt-restart state, including short-term interruption, medium-term interruption, and long-term interruption. Specifically, the PLC system reads the timestamps of the interruption start time and restart time, calculates the difference between the two times to obtain the interruption duration, and then compares it with a preset duration threshold to automatically classify the interruption type. For example, the threshold is set as follows: short-term interruption less than 5 minutes, medium-term interruption greater than or equal to 5 minutes and less than or equal to 30 minutes, and long-term interruption greater than 30 minutes. The system directly determines and marks the current event as belonging to which category based on the duration value.

[0052] Step S650: Set the number of segments in the second molding control parameter set according to the short-term, medium-term, and long-term interruptions, with the number of segments increasing sequentially for each type. Specifically, the number of segments in the control curve is automatically allocated based on the interruption type. Short-term interruptions have a small thermal history impact, so fewer segments are used to simplify control and reduce oscillations; medium-term interruptions have a moderate impact, so a moderate number of segments are used; long-term interruptions have a deep temperature drop and significant uneven cross-linking, requiring more segments for fine compensation. For example, short-term interruptions use 2-stage heating + 2-stage pressure control, medium-term interruptions use 3-stage heating + 3-stage pressure control, and long-term interruptions use 4 or 5-stage heating + 4 or 5-stage pressure control. Each segment includes a target value, holding time, and acceleration / deceleration rate, forming a complete and executable segmented control curve.

[0053] This application employs a method to detect whether the rubber pad vulcanization molding production line is in an interruption-restart state. If it is determined to be in this state, the molding state before the interruption and after the restart, as well as the control parameter dataset before the interruption, are collected. Then, the crosslinking degree distribution matrix is ​​calculated based on these data. By combining the interruption-restart sample database, similar sample sets are retrieved, and the top N similar control parameter sets that meet the molding quality standards are selected. This expands multiple sets of candidate control parameters and optimizes them with the goal of maximizing molding quality, generating a new set of molding control parameters that can compensate for the impact of interruption thermal history. Based on this new set of parameters, the vulcanization molding process of the production line is controlled. This solves the technical problems of existing automotive engine rubber pad vulcanization molding process control, such as the inability to effectively compensate for the impact of interruption and the easy occurrence of molding quality defects. It achieves the technical effect of effectively compensating for the impact of production line interruption, reducing molding quality defects, and ensuring stable vulcanization molding quality.

[0054] In the above text, refer to Figure 1 A method for controlling the vulcanization molding process of automotive engine rubber gaskets according to embodiments of the present invention is described in detail. Next, reference will be made to... Figure 2 A control system for the vulcanization molding process of automotive engine rubber gaskets according to an embodiment of the present invention is described.

[0055] The control system for the vulcanization molding process of automotive engine rubber pads according to embodiments of the present invention addresses the technical problems of existing automotive engine rubber pad vulcanization molding process control, such as the inability to effectively compensate for the impact of interruptions and the susceptibility to molding quality defects. It achieves the technical effect of effectively compensating for the impact of production line interruptions, reducing molding quality defects, and ensuring stable vulcanization molding quality. The control system for the automotive engine rubber pad vulcanization molding process includes: a state detection module 10, a dataset acquisition module 20, a crosslinking degree distribution matrix calculation module 30, a similar sample set retrieval module 40, a screening module 50, a second molding control parameter set generation module 60, and a vulcanization molding control module 70.

[0056] The status detection module 10 is used to detect whether the current rubber pad vulcanization molding production line is in an interruption-restart state; the dataset acquisition module 20 is used to acquire interruption-restart data from the timing window before the interruption if it is in an interruption-restart state, including the first molding state dataset, the first molding control parameter set, and the second molding state dataset of the interruption-restart timing window; the crosslinking degree distribution matrix calculation module 30 is used to calculate the crosslinking degree distribution matrix based on the first molding state dataset and the second molding state dataset; the similar sample set retrieval module 40 is used to perform a retrieval based on the interruption-restart sample database to obtain a set of similar samples corresponding to the crosslinking degree distribution matrix; the filtering module 50 is used to filter samples based on the... The system describes a set of similar second molding control parameters corresponding to a set of similar samples and corresponding vulcanization molding quality indicators. It then obtains the top N similar second molding control parameter sets whose vulcanization molding quality indicators are greater than a preset threshold. A second molding control parameter set generation module 60 is used to expand candidate control parameters based on the N similar second molding control parameter sets, obtaining N sets of candidate second molding control parameter sets. The optimization objective is to maximize the vulcanization molding quality indicators within these N sets of candidate second molding control parameter sets, generating a second molding control parameter set to compensate for the historical impact of interrupted heat. A vulcanization molding control module 70 is used to perform vulcanization molding control on the current rubber pad vulcanization molding production line according to the second molding control parameter set.

[0057] The detailed description of the specific configuration of the similar sample set retrieval module 40 is explained as follows: As mentioned above, the similar sample set retrieval module 40 may further include: constructing an interruption-restart sample database, wherein the interruption-restart sample database includes a first molding state data sample set, a first molding control parameter sample set, a second molding state data sample set, a second molding control parameter sample set, and labels characterizing vulcanization molding quality based on the interruption-restart event samples; wherein, the first molding control parameter sample set is the pre-interruption vulcanization molding control parameters of the rubber pad corresponding to the first molding state data sample set, and the second molding control parameter sample set is the post-interruption-restart vulcanization molding control parameters of the rubber pad corresponding to the second molding state data sample set.

[0058] The crosslinking degree distribution matrix is ​​calculated based on the first molding state dataset and the second molding state dataset. The crosslinking degree distribution matrix calculation module 30 may further include: a region division unit for dividing the rubber pad into multiple local regions according to the molding thickness, each local region corresponding to a crosslinking degree sub-matrix unit; a calculation unit for calculating the cumulative vulcanization time before interruption for each local region in the multiple local regions based on the first molding state dataset, and calculating the temperature decay curve during interruption for each local region in the multiple local regions based on the second molding state dataset; an equivalent vulcanization time calculation unit for calculating the equivalent vulcanization time based on the cumulative vulcanization time before interruption and the temperature decay curve during interruption; and a crosslinking degree calculation unit for calculating the crosslinking degree of each local region based on the equivalent vulcanization time and local pressure index, thereby generating a crosslinking degree distribution matrix.

[0059] The calculation unit may further include: the temperature decay curve during the interruption is obtained by introducing an interruption temperature decay function, which is obtained by performing decay and degradation analysis on the first formed state dataset based on the obtained interruption cumulative timing window.

[0060] The optimization objective is to maximize the vulcanization molding quality index. The optimization is performed on the N sets of candidate second molding control parameters to generate a second molding control parameter set used to compensate for the impact of interrupted thermal history. The second molding control parameter set generation module 60 may further include: an N-candidate second molding control parameter set selection unit for selecting N candidate second molding control parameter sets from the N sets; a crosslinking evolution quality prediction unit for simultaneously calculating the crosslinking evolution quality prediction model on the N candidate second molding control parameter sets and outputting N vulcanization molding quality indices; and a second molding control parameter set output unit for searching for N candidate second molding control parameter sets in the next iteration round based on the N vulcanization molding quality indices from the N sets of candidate second molding control parameter sets using gradient descent, until the rate of change of the optimal molding vulcanization molding quality index in consecutive iteration rounds is less than a preset threshold, and outputting the second molding control parameter set. The second molding control parameter set includes at least a segmented heating curve, a segmented pressure recovery curve, and a compensation vulcanization time.

[0061] The calculation unit, which calculates the cumulative vulcanization time before interruption for each of the plurality of local regions based on the first molding state dataset, may further include: a time curve extraction component for extracting the first temperature-time curve and the first pressure-time curve for each local region based on the first molding state dataset, which includes the mold temperature field distribution, rubber dielectric response, and cavity pressure timing window before interruption; and a cumulative vulcanization time calculation component for obtaining the cumulative vulcanization time before interruption by integrating the reaction rate on the first temperature-time curve and correcting the reaction rate integration based on the first pressure-time curve.

[0062] The calculation unit may further include: a second temperature-time curve acquisition component for acquiring the second temperature-time curve of each local region during interruption, based on the second molding state dataset including the mold temperature field distribution, dielectric response of the rubber material, and cavity pressure timing during the interruption restart window; and an interruption-time temperature decay curve establishment component for analyzing the temperature field change trends of the first temperature-time curve and the second temperature-time curve to establish the interruption-time temperature decay curve of each local region.

[0063] The second molding control parameter set generation module 60, which generates a second molding control parameter set to compensate for the impact of interrupted thermal history, may further include: a status type acquisition unit for acquiring the type of the interrupt-restart status, including short-term interruption, medium-term interruption, and long-term interruption; and a segment number setting unit for setting the number of segments of the second molding control parameter set according to the short-term interruption, medium-term interruption, and long-term interruption, wherein the number of segments of the short-term interruption, medium-term interruption, and long-term interruption increases sequentially.

[0064] The control system for the vulcanization molding process of automotive engine rubber pads provided in this embodiment of the invention can execute the control method for the vulcanization molding process of automotive engine rubber pads provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0065] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0066] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for controlling the vulcanization molding process of automotive engine rubber gaskets, characterized in that, The method includes: Check if the current rubber pad vulcanization molding production line is in an interruption-restart state; If in an interrupt-restart state, collect the interrupt-restart data of the timing window before the interruption, including the first forming state dataset, the first forming control parameter set, and the second forming state dataset of the interrupt-restart timing window; Calculate the crosslinking degree distribution matrix based on the first molding state dataset and the second molding state dataset; By combining the interrupted-restart sample database for retrieval, a set of similar samples corresponding to the crosslinking degree distribution matrix is ​​obtained; Based on the similar second molding control parameter set corresponding to the similar sample set and the corresponding vulcanization molding quality index, obtain the first N similar second molding control parameter sets whose vulcanization molding quality index is greater than a preset threshold. Based on the N similar second molding control parameter sets, candidate control parameters are expanded to obtain N sets of candidate second molding control parameter sets. The optimization objective is to maximize the vulcanization molding quality index. The optimization is performed on the N sets of candidate second molding control parameter sets to generate a second molding control parameter set used to compensate for the influence of interrupted heat history. Vulcanization molding control is performed on the current rubber pad vulcanization molding production line according to the second molding control parameter set; The crosslinking degree distribution matrix is ​​calculated based on the first molding state dataset and the second molding state dataset, using the following method: The rubber pad is divided into multiple local regions according to the molding thickness, and each local region corresponds to a cross-linking degree sub-matrix unit; The cumulative vulcanization time before interruption is calculated for each of the plurality of local regions based on the first molding state dataset, and the temperature decay curve during interruption is calculated for each of the plurality of local regions based on the second molding state dataset. The equivalent vulcanization time is calculated based on the cumulative vulcanization time before the interruption and the temperature decay curve during the interruption. The degree of crosslinking in each local region is calculated based on the equivalent vulcanization time and local pressure index, generating a crosslinking degree distribution matrix.

2. The method for controlling the vulcanization molding process of automotive engine rubber gaskets as described in claim 1, characterized in that, Construct an interruption-restart sample database, which includes a first molding state data sample set, a first molding control parameter sample set, a second molding state data sample set, a second molding control parameter sample set, and labels characterizing vulcanization molding quality based on interruption-restart event samples; Wherein, the first molding control parameter sample set is the rubber pad vulcanization molding control parameter before interruption corresponding to the first molding state data sample set, and the second molding control parameter sample set is the rubber pad vulcanization molding control parameter after interruption restart corresponding to the second molding state data sample set.

3. The method for controlling the vulcanization molding process of automotive engine rubber gaskets as described in claim 1, characterized in that, The temperature decay curve during the interruption is obtained by introducing an interruption temperature decay function, which is obtained by performing decay and degradation analysis on the first formed state dataset based on the obtained interruption cumulative timing window.

4. The method for controlling the vulcanization molding process of automotive engine rubber gaskets as described in claim 1, characterized in that, The optimization objective is to maximize the vulcanization molding quality index. This optimization is performed on the N sets of candidate second molding control parameters to generate a second molding control parameter set used to compensate for the effects of interrupted thermal history. The method includes: N candidate sets of second molding control parameters are selected from the N sets of candidate second molding control parameters respectively; The crosslinking evolution quality prediction model is simultaneously calculated for the N candidate second molding control parameter sets, and N vulcanization molding quality indicators are output. Based on the N vulcanization molding quality indicators, the N candidate second molding control parameter sets for the next iteration are searched by gradient descent from the N sets of candidate second molding control parameter sets until the rate of change of the optimal molding vulcanization molding quality indicators in consecutive iterations is less than a preset threshold, and the second molding control parameter set is output. The second set of molding control parameters includes at least a segmented heating curve, a segmented pressure recovery curve, and a compensated vulcanization time.

5. The method for controlling the vulcanization molding process of automotive engine rubber gaskets as described in claim 1, characterized in that, The method for calculating the cumulative vulcanization time before interruption for each of the multiple local regions based on the first molding state dataset includes: The first molding state dataset includes the mold temperature field distribution, the dielectric response of the rubber material, and the cavity pressure timing of the timing window before the interruption. Based on the first molding state dataset, extract the first temperature-time curve and the first pressure-time curve for each local region; By integrating the reaction rate on the first temperature-time curve and correcting the reaction rate integral based on the first pressure-time curve, the cumulative vulcanization time before interruption is obtained.

6. The method for controlling the vulcanization molding process of automotive engine rubber gaskets as described in claim 5, characterized in that, The method for calculating the temperature decay curve during the interruption period for each of the plurality of local regions based on the second molding state dataset includes: The second molding state dataset includes the mold temperature field distribution, the dielectric response of the rubber material, and the cavity pressure timing during the interruption restart timing window; Obtain the second temperature-time curve for each local region interrupted and restarted; By analyzing the temperature field change trends of the first temperature-time curve and the second temperature-time curve, a temperature decay curve during the interruption period of each local region is established.

7. The method for controlling the vulcanization molding process of automotive engine rubber gaskets as described in claim 1, characterized in that, The method for generating a second set of molding control parameters to compensate for the effects of interrupted thermal history also includes: Obtain the type of the interrupt-restart status, including short interrupt, medium interrupt, and long interrupt; The number of segments in the second molding control parameter set is set according to the short-term interrupt, medium-term interrupt and long-term interrupt respectively, wherein the number of segments of the short-term interrupt, medium-term interrupt and long-term interrupt increases sequentially.

8. A control system for the vulcanization molding process of automotive engine rubber gaskets, characterized in that, The system is used to implement the control method for the vulcanization molding process of automotive engine rubber gaskets according to any one of claims 1-7, the system comprising: The status detection module is used to detect whether the current rubber pad vulcanization molding production line is in an interrupted-restart state; The dataset acquisition module is used to collect interrupt-restart data from the timing window before the interruption if the interruption-restart state is in progress. This includes the first forming state dataset, the first forming control parameter set, and the second forming state dataset of the interrupt-restart timing window. The crosslinking degree distribution matrix calculation module is used to calculate the crosslinking degree distribution matrix based on the first molding state dataset and the second molding state dataset. The similar sample set retrieval module is used to perform retrieval in conjunction with the interrupted-restarted sample database to obtain a similar sample set corresponding to the crosslinking degree distribution matrix. The filtering module is used to obtain the top N similar second molding control parameter sets whose vulcanization molding quality index is greater than a preset threshold, based on the similar second molding control parameter set corresponding to the similar sample set and the corresponding vulcanization molding quality index. The second molding control parameter set generation module is used to expand candidate control parameters based on the N similar second molding control parameter sets, obtain N sets of candidate second molding control parameter sets, optimize the N sets of candidate second molding control parameter sets with the optimization objective of maximizing the vulcanization molding quality index, and generate a second molding control parameter set for compensating for the influence of interrupted heat history. The vulcanization molding control module is used to control the vulcanization molding of the current rubber pad vulcanization molding production line according to the second molding control parameter set.

Images