Adjusting method and system for self-adaptive optimization of dispensing machine

Abstract

The invention relates to the technical field of dispensing machine optimization, in particular to an adjusting method and system for self-adaptive optimization of a dispensing machine. The method comprises the following steps: identifying defective dispensing abnormal execution parameters by acquiring a dispensing machine operation log and mapping abnormal execution parameters; then, carrying out curing cross-linking abnormity derivation on defect parameters, quantifying interface bonding force deficiency, and further evaluating the sealing efficiency weakening degree; then, based on the sealing efficiency weakening degree data, interface multi-section curing requirements are analyzed, and then self-adaptive correction of the dispensing process is carried out; and finally, designing automatic firmware through the self-adaptive correction data, and embedding the automatic firmware into a control center to realize self-adaptive optimization of the dispensing machine. According to the invention, the optimization technology of the dispensing machine is optimized, so that the optimization technology of the dispensing machine is more perfect.

Description

Technical Field

[0001] The present invention relates to the technical field of dispenser optimization, and particularly to an adjustment method and system for self-adaptive optimization of a dispenser. Background Art

[0002] The dispensing process is widely used in modern manufacturing industries, especially in the fields of electronics, automotive, medical equipment, etc. The dispenser undertakes important production tasks. The main function of the dispenser is to accurately dispense glue or other adhesives at designated positions to ensure the structural and functional integrity of products. With the advancement of intelligent manufacturing and Industry 4.0, more and more automation technologies and intelligent control methods have been introduced into the production process. In order to improve the working efficiency and stability of the dispenser and reduce the cost of manual intervention, it has become particularly important to develop an adjustment method for the dispensing process based on self-adaptive optimization. However, there is a problem in a traditional adjustment method for self-adaptive optimization of a dispenser that the analysis of the weakening degree of the dispensing interface seal is inaccurate, resulting in large dispensing errors in the dispensing process. Summary of the Invention

[0003] Based on this, it is necessary to provide an adjustment method and system for self-adaptive optimization of a dispenser to solve at least one of the above technical problems.

[0004] To achieve the above object, an adjustment method for self-adaptive optimization of a dispenser, the method includes the following steps: Step S1: Obtain the operation log of the dispenser; perform mapping of dispensing abnormal execution parameters on the operation log of the dispenser to obtain defective dispensing abnormal execution parameters; Step S2: Deduce the curing cross-linking abnormality of the glue strip for the defective dispensing abnormal execution parameters to obtain glue strip curing cross-linking abnormal data; quantify the lack of interfacial bonding force for the glue strip curing cross-linking abnormal data to obtain interfacial bonding force lack quantification data; evaluate the weakening degree of the sealing effectiveness based on the interfacial bonding force lack quantification data to obtain sealing effectiveness weakening degree data; Step S3: Analyze and resolve the multi-stage curing requirements control of the interface according to the sealing effectiveness weakening degree data to obtain interface multi-stage curing requirements control data; perform self-adaptive correction of the dispensing process on the defective dispensing abnormal execution parameters based on the interface multi-stage curing requirements control data to obtain self-adaptive logic correction data for the dispensing process; Step S4: Design an automated firmware based on the self-adaptive logic correction data for the dispensing process to obtain a self-adaptive correction firmware for the dispensing process, and embed the self-adaptive correction firmware for the dispensing process into the control center to perform self-adaptive optimization of the dispenser.

[0005] Preferably, step S1 includes the following steps: Step S11: Obtain the operation log of the dispenser; Step S12: Extract the historical task execution records from the operation log of the dispensing machine to obtain the historical operation task execution records; Step S13: Extract the strip defect status from the historical operation task execution records to obtain the strip defect status; Step S14: Map the dispensing abnormal execution parameters to the operation log of the dispensing machine according to the strip defect status to obtain the defective dispensing abnormal execution parameters.

[0006] Preferably, step S2 includes the following steps: Step S21: Obtain the glue raw material data; perform morphological defect analysis on the strip defect status to obtain the strip morphological defect data; Step S22: Derive the abnormal dispensing curing crosslinking density based on the strip morphological defect data and the glue raw material data for the defective dispensing abnormal execution parameters to obtain the strip curing crosslinking density abnormal data; Step S23: Quantify the lack of interfacial bonding force for the strip curing crosslinking abnormal data to obtain the quantified data of the lack of interfacial bonding force; Step S24: Evaluate the degree of weakening of the sealing efficiency based on the strip curing crosslinking density abnormal data and the quantified data of the lack of interfacial bonding force to obtain the data of the degree of weakening of the sealing efficiency.

[0007] Preferably, step S22 includes the following steps: Step S221: Analyze the crack density of the strip morphological defect data to obtain the strip crack density data; Step S222: Evaluate the bubble depth of the strip morphological defect data to obtain the strip defect bubble depth data; Step S223: Reverse solve the curing pressure imbalance for the defective dispensing abnormal execution parameters according to the strip crack density data and the strip defect bubble depth data to obtain the curing pressure imbalance data; Step S224: Calculate the raw material volume shrinkage ratio based on the glue raw material data and the curing pressure imbalance data to obtain the volume shrinkage ratio of the curing imbalance raw material; Step S225: Analyze the internal thermal residual stress for the volume shrinkage ratio of the curing imbalance raw material to obtain the internal thermal residual stress; Step S226: Derive the abnormal dispensing curing crosslinking density based on the volume shrinkage ratio of the curing imbalance raw material and the internal thermal residual stress to obtain the strip curing crosslinking density abnormal data.

[0008] Preferably, step S3 includes the following steps: Step S31: Perform normalization processing on the data of the degree of weakening of the sealing efficiency to obtain the normalized data of the weakening of the sealing efficiency; Step S32: Analyze the interface multi-stage curing requirement control based on the normalized data of the weakened sealing efficiency to obtain the interface multi-stage curing requirement control data; Step S33: Based on the interface multi-stage curing requirement control data, adaptively correct the dispensing process parameters for defective dispensing anomalies to obtain the dispensing process adaptive correction data; Step S34: Perform logical learning on the dispensing process adaptive correction data to obtain the dispensing process adaptive logic correction data.

[0009] Preferably, step S32 includes the following steps: Step S321: Deduce the temperature change sensitivity of the normalized data of the weakened sealing efficiency to obtain the sealing weakening temperature change sensitivity data; Step S322: Evaluate the expansion / contraction fatigue failure stress based on the sealing weakening temperature change sensitivity data to obtain the expansion / contraction fatigue failure stress data; Step S323: Identify the non-linear relationship of the sealing weakening temperature change sensitivity data to generate a weakening-temperature non-linear relationship curve; Calculate the interface contact temperature control tolerance based on the weakening-temperature non-linear relationship curve to obtain the interface contact temperature control tolerance; Step S324: Control the temperature change rate of the interface contact dispensing according to the interface contact temperature control tolerance and the weakening-temperature non-linear relationship curve to obtain the interface contact temperature change rate; Step S325: Analyze the interface multi-stage temperature curing control requirements according to the interface contact temperature control tolerance and the interface contact temperature change rate to obtain the temperature curing requirement control data; Step S326: Analyze the interface pressure curing control requirements based on the expansion / contraction fatigue failure stress data and the temperature curing requirement control data to obtain the pressure curing control requirement data; Step S327: Analyze the interface multi-stage curing requirement control according to the temperature curing requirement control data and the pressure curing control requirement data to obtain the interface multi-stage curing requirement control data.

[0010] Preferably, step S4 includes the following steps: Step S41: Perform coding processing on the dispensing process adaptive logic correction data to obtain the dispensing process adaptive correction code; Step S42: Based on the dispensing process adaptive correction code, perform automated firmware design to obtain the dispensing process adaptive correction firmware, and embed the dispensing process adaptive correction firmware into the control center to perform the adaptive optimization of the dispenser.

[0011] Preferably, the present invention further provides an adjustment system for self - adaptive optimization of a dispensing machine, which is used to execute the adjustment method for self - adaptive optimization of the dispensing machine as described above. The adjustment system for self - adaptive optimization of the dispensing machine includes: An abnormal execution parameter mapping module, which is used to obtain the operation log of the dispensing machine; perform mapping of abnormal execution parameters of dispensing on the operation log of the dispensing machine to obtain defective dispensing abnormal execution parameters; A sealing efficiency weakening evaluation module, which is used to deduce abnormal curing cross - linking of dispensing for the defective dispensing abnormal execution parameters to obtain abnormal data of strip curing cross - linking; quantify the lack of interfacial bonding force for the abnormal data of strip curing cross - linking to obtain quantified data of the lack of interfacial bonding force; evaluate the degree of weakening of the sealing efficiency based on the quantified data of the lack of interfacial bonding force to obtain data on the degree of weakening of the sealing efficiency; An adaptive logic correction module, which is used to perform control analysis of multi - stage curing requirements at the interface according to the data on the degree of weakening of the sealing efficiency to obtain control data on multi - stage curing requirements at the interface; perform self - adaptive correction of the dispensing process on the defective dispensing abnormal execution parameters based on the control data on multi - stage curing requirements at the interface to obtain self - adaptive logic correction data for the dispensing process; An automated firmware design module, which is used to perform automated firmware design based on the self - adaptive logic correction data for the dispensing process to obtain a self - adaptive correction firmware for the dispensing process, and embed the self - adaptive correction firmware for the dispensing process into the control center to execute self - adaptive optimization of the dispensing machine.

[0012] The beneficial effects of the present invention are as follows: By obtaining the operation logs of the dispensing machine and mapping the dispensing anomaly execution parameters in the logs, defects in the dispensing process can be accurately identified. The core of this process is to convert the operation logs into actionable defect data, providing a basis for quantitative analysis of dispensing anomalies. This enables subsequent optimization of the dispensing process to have clear, data-driven goals, improving the dispensing quality and production stability. The defect dispensing anomaly execution parameters are further deduced into data on abnormal curing and crosslinking of the glue strip, and the amount of missing interfacial bonding force is quantified. This quantification process helps to accurately analyze the curing and crosslinking state of the glue strip, further understand the bonding quality between the glue strip and the substrate, and ultimately evaluate the degree of weakening of the sealing effectiveness. Through this step, the key factors affecting the sealing effect can be identified, providing a quantitative basis for subsequent process adjustment and optimization. According to the data on the degree of weakening of the sealing effectiveness, the control analysis of the multi-stage curing requirements of the interface can determine the optimal segmentation scheme for the curing of the glue strip during the dispensing process, ensuring that the glue strip is properly cured at different stages, thereby optimizing the interfacial bonding force. By adaptively correcting the dispensing anomaly execution parameters based on this requirement control data, the dispensing process can be precisely adjusted, potential quality problems can be corrected, the overall dispensing quality can be improved, and the defective product rate can be reduced. Based on the adaptive logic correction data obtained from the previous steps, an automated dispensing process correction firmware is designed and embedded into the control center of the dispensing machine. Through this firmware, the dispensing machine can self-adjust according to real-time data and continuously optimize the dispensing process. This step not only improves the production efficiency by automatically adjusting the dispensing process, but also greatly enhances the flexibility and accuracy of production, and can maintain consistent product quality in a changing production environment, ensuring the continuous and stable operation of the production line. Therefore, the present invention is an optimized treatment for a traditional method of self-adaptive optimization adjustment of a dispensing machine, solving the problem that the traditional method of self-adaptive optimization adjustment of a dispensing machine has inaccurate analysis of the degree of weakening of the dispensing interface seal, resulting in large dispensing errors in the dispensing process, improving the accuracy of analysis of the degree of weakening of the dispensing interface seal, and reducing the dispensing error of the dispensing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic flow chart of the steps of a method for self-adaptive optimization adjustment of a dispensing machine; Figure 2 is Figure 1 a detailed implementation step flow chart of step S2 in; Figure 3 is Figure 1 a detailed implementation step flow chart of step S3 in. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] Please refer to Figures 1 to 3 , a method for self-adaptive optimization adjustment of a dispensing machine, the method comprising the following steps: Step S1: Obtain the operation log of the dispensing machine; perform mapping of dispensing anomaly execution parameters on the operation log of the dispensing machine to obtain defective dispensing anomaly execution parameters; Step S2: Deduce the curing and cross-linking anomalies of the glue strip for the defective dispensing anomaly execution parameters to obtain glue strip curing and cross-linking anomaly data; quantify the lack of interfacial bonding force for the glue strip curing and cross-linking anomaly data to obtain quantified data on the lack of interfacial bonding force; evaluate the degree of weakening of the sealing efficiency based on the quantified data on the lack of interfacial bonding force to obtain data on the degree of weakening of the sealing efficiency; Step S3: Analyze the control requirements for multi-stage curing of the interface based on the data on the degree of weakening of the sealing efficiency to obtain control data for multi-stage curing requirements of the interface; perform adaptive correction of the dispensing process on the defective dispensing anomaly execution parameters based on the control data for multi-stage curing requirements of the interface to obtain data on the adaptive logic correction of the dispensing process; Step S4: Design an automated firmware based on the data on the adaptive logic correction of the dispensing process to obtain an adaptive correction firmware for the dispensing process, and embed the adaptive correction firmware for the dispensing process into the control center to perform adaptive optimization of the dispensing machine.

[0015] In the embodiment of the present invention, refer to Figure 1 As described, it is a schematic diagram of the step flow of a method for adaptive optimization adjustment of a dispensing machine according to the present invention. In this example, the method for adaptive optimization adjustment of the dispensing machine includes the following steps: Step S1: Obtain the operation log of the dispensing machine; perform mapping of dispensing anomaly execution parameters on the operation log of the dispensing machine to obtain defective dispensing anomaly execution parameters; In the embodiments of the present invention, first, the operation log of the dispenser needs to be obtained through the data acquisition system of the dispenser. This log records various parameters during the operation of the dispenser, such as dispensing speed, dispensing volume, glue temperature, pressure, and time. To process these log data, log data analysis technology is adopted to parse the log file and map different operation events to timestamps through programming methods. During this process, by extracting the execution records of historical tasks, dispensing events with anomalies during execution can be screened out. Once the operation log of the dispenser is obtained, the next step is to map the dispensing anomaly execution parameters of the operation log. At this time, a rule-based mapping method is adopted to identify and classify the anomalies that occur when the dispenser executes tasks. Specifically, first, a set of standard parameter ranges (such as dispensing speed, glue flow rate, etc.) are set as reference values under normal working conditions. When the actual execution parameters exceed these standard ranges, it is considered that a dispensing anomaly has occurred. By introducing a "threshold exceeded" inspection mechanism in the data, these exceeded data are marked as "anomalous" and classified. The specific method of classification is to further distinguish the anomaly types, such as dispensing volume anomaly, speed anomaly, pressure anomaly, etc., and finally obtain a set of "defective dispensing anomaly execution parameters", that is, the abnormal dispensing execution conditions.

[0016] Step S2: Deduce the dispensing curing cross-linking anomaly from the defective dispensing anomaly execution parameters to obtain the glue strip curing cross-linking anomaly data; quantify the lack of interfacial bonding force for the glue strip curing cross-linking anomaly data to obtain the quantified data of the lack of interfacial bonding force; evaluate the degree of weakening of the sealing efficiency based on the quantified data of the lack of interfacial bonding force to obtain the data of the degree of weakening of the sealing efficiency; In the embodiments of the present invention, first, the dispensing curing cross-linking density anomaly is deduced from the defective dispensing anomaly execution parameters. This process involves a detailed analysis of the curing process of the glue strip, especially the change in its cross-linking density. During the dispensing process, the curing of the glue is a key chemical reaction, and the cross-linking density of the glue during the curing process directly affects the performance of the final product. Therefore, first, the raw material data of the glue needs to be collected and synchronously analyzed in combination with the operation log of the dispenser. By analyzing the conditions such as temperature and pressure during the curing process item by item, the change in the cross-linking density is deduced using the curing kinetics equation. The cross-linking process of the glue follows a standard curing equation, such as the following expression: , where, is the cross-linking density, is the time value required for curing, is the activation energy, is the gas constant, is the temperature. By monitoring the data of various parameters during the operation of the dispensing machine and combining with the curing equation of the glue, the abnormal data of the curing crosslinking density of the glue strip can be deduced. Next, based on the abnormal data of the glue strip curing crosslinking, the interfacial bonding force between the glue strip and the substrate is quantified through the interfacial mechanics theory. Using the basic theory of interfacial bonding force, the interfacial force is determined by the physical and chemical properties of the material and the curing conditions. Mechanical models (such as molecular dynamics simulation, elastic mechanics model, etc.) are used for simulation calculation, and finally the quantified data of the lack of interfacial bonding force is obtained. This quantified data represents the strength of the interfacial bonding between the glue strip and the substrate. Finally, based on the quantified data of the lack of interfacial bonding force, the degree of weakening of the sealing efficiency is evaluated. This process is evaluated and analyzed by establishing the mathematical relationship between the interfacial bonding force and the sealing efficiency (such as the relationship between the bonding force and the leakage rate) to obtain the data of the degree of weakening of the sealing efficiency.

[0017] Step S3: Analyze the multi-stage curing requirements control of the interface according to the data of the degree of weakening of the sealing efficiency to obtain the multi-stage curing requirements control data of the interface; based on the multi-stage curing requirements control data of the interface, adaptively correct the dispensing process of the abnormal execution parameters of the defective dispensing to obtain the adaptive logic correction data of the dispensing process; In the embodiment of the present invention, according to the data of the degree of weakening of the sealing efficiency, the multi-stage curing requirements control of the interface is analyzed. In order to ensure that the sealing efficiency is effectively restored, a multi-stage control strategy of temperature and pressure must be implemented during the curing process. First, the data of the degree of weakening of the sealing efficiency is normalized to obtain the normalized data of the degree of weakening of the sealing efficiency for comparison with other control parameters. Then, based on these data, the temperature control requirements analysis of the multi-stage curing process is carried out. For the generation of the multi-stage curing requirements control data, an empirical-based control method and a thermodynamic analysis model are used. During the curing process, different temperature and pressure conditions will affect the crosslinking effect of the glue. Therefore, through the regression analysis of the data of the degree of weakening of the sealing efficiency, the influence law of the temperature and pressure changes on the curing process is obtained, and specific curing requirements control data are generated based on these laws. Next, based on the multi-stage curing requirements control data of the interface, the dispensing process of the abnormal execution parameters of the defective dispensing is adaptively corrected. Here, an adaptive control algorithm (such as PID control or fuzzy control) is used to adjust the execution parameters (such as dispensing speed, glue volume, glue temperature, etc.) of the dispensing machine in real time according to the curing requirements control data. The adaptive algorithm can dynamically adjust the working parameters of the dispensing machine according to the feedback of environmental changes and historical data, so as to optimize the dispensing process.

[0018] Step S4: Design the automatic firmware based on the adaptive logic correction data of the dispensing process to obtain the adaptive correction firmware of the dispensing process, and embed the adaptive correction firmware of the dispensing process into the control center to execute the adaptive optimization of the dispensing machine.

[0019] In the embodiments of the present invention, the automatic firmware is designed based on the self - adaptive logic correction data of the dispensing process. In this design process, first, the firmware architecture of the control center needs to be modified according to the logic correction data to design a firmware program suitable for the new dispensing process. During the firmware design process, according to the dispensing process self - adaptive correction data obtained in step S3, these data need to be converted into control instructions and the corresponding control program is written. This process is usually developed using embedded programming languages (such as C language, assembly language) to ensure that the firmware can be efficiently executed in the dispensing machine control system. After the design is completed, the automatic firmware is embedded into the control center of the dispensing machine, and the control center usually includes a hardware interface and a software control module. The firmware will adjust the execution parameters of the dispensing machine in real - time according to the control requirements to ensure that the dispensing process achieves the expected effect, thus realizing the self - adaptive optimization of the dispensing machine.

[0020] Step S1 includes the following steps: Step S11: Obtain the operation log of the dispensing machine; Step S12: Extract the historical task execution records from the operation log of the dispensing machine to obtain the historical operation task execution records; Step S13: Extract the strip defect status from the historical operation task execution records to obtain the strip defect status; Step S14: Map the abnormal dispensing execution parameters to the operation log of the dispensing machine according to the strip defect status to obtain the defective dispensing abnormal execution parameters.

[0021] In the embodiments of the present invention, first, it is necessary to obtain the operation log from the control system of the dispensing machine. This log contains the key information recorded by the dispensing machine during various tasks, including operation parameters (such as dispensing speed, glue flow rate, glue temperature, dispensing pressure, etc.), operation time, machine status, and error reports. The dispensing machine collects this information in real time through sensors and data recording modules to generate a structured log file. The way to obtain the log is usually to perform remote or local data download through the control system of the dispensing machine, and store the data in a database or a log file system for subsequent processing. Then, extract the historical task execution records of the dispensing machine operation log. There are multiple tasks during the operation of the dispensing machine, and each task contains different dispensing operations. In the process of extracting historical task execution records, first, sort and filter the data according to the timestamps of the log files, and select the operation data corresponding to a specific time period or task number. Through programming means, parse the fields in the log file, such as task ID, time interval, dispensing parameters, etc., extract the execution details of each task, and organize them into structured historical task data. Subsequently, extract the strip defect status from the extracted historical task execution records. The strip defect status usually refers to the quality problems of the strip during the dispensing process, such as defects like bubbles, cracks, or incomplete cross-linking in the strip. This process uses a special defect detection algorithm to make judgments based on known strip quality standards and the working status of the dispensing machine. First, based on the key parameters such as glue temperature, pressure, and flow rate in the historical task execution records, combined with the defect characteristics given in empirical data or literature, detect the strip defect status occurring during the dispensing process. The extraction of the strip defect status is carried out through an outlier detection algorithm, where the standard quality data is compared with the actual records. If a certain parameter exceeds the predetermined threshold range, it is considered that there is a defect in the dispensing process. For example, when the glue flow rate suddenly becomes low, it causes the strip to be uneven, resulting in a defect. Finally, perform mapping of abnormal dispensing execution parameters on the dispensing machine operation log based on the strip defect status. The key to this step is to identify abnormal execution parameters by comparing the strip defect status with the operation parameters in the dispensing machine log and perform mapping. By establishing a threshold model for abnormal dispensing parameters, it can be determined which dispensing operations have parameter deviations. Further, perform correlation analysis between these abnormal dispensing parameters and the strip defect status to judge which abnormal parameters directly affect the occurrence of strip defects. Through the abnormal parameter mapping algorithm, a set of defective dispensing abnormal execution parameters can be generated, and these parameters will play a crucial role in subsequent process corrections.

[0022] Step S2 includes the following steps: Step S21: Obtain glue raw material data; perform morphological defect analysis on the strip defect status to obtain strip morphological defect data; Step S22: Derive the abnormal dispensing curing crosslinking density of the defective dispensing execution parameters based on the strip form defect data and the glue raw material data to obtain the strip curing crosslinking density abnormal data; Step S23: Quantify the lack of interfacial bonding force for the strip curing crosslinking abnormal data to obtain the quantified data of the lack of interfacial bonding force; Step S24: Evaluate the degree of weakening of the sealing effectiveness based on the strip curing crosslinking density abnormal data and the quantified data of the lack of interfacial bonding force to obtain the data of the degree of weakening of the sealing effectiveness.

[0023] As an example of the present invention, refer to Figure 2 As shown, in this example, the said step S2 includes: Step S21: Obtain the glue raw material data; perform a morphological defect analysis on the strip defect state to obtain the strip form defect data; In the embodiment of the present invention, it is first necessary to obtain relevant data of the glue raw material. These data mainly include the basic physical and chemical properties of the glue, such as viscosity, density, surface tension, curing time, coefficient of thermal expansion, crosslinking agent content, etc. To ensure the accuracy of the obtained data, it is necessary to obtain the detailed technical specifications of the product from the glue manufacturer or obtain it through experimental measurement. The acquisition of the glue raw material can be monitored in real time through a sensor data acquisition system, record and store these data. By sorting out the performance data of the glue, a complete set of raw material data sets can be obtained. During the strip form defect analysis process, the focus is on evaluating the strip form defects. Strip form defects usually manifest as problems such as an uneven surface, the presence of bubbles, cracks, or uneven thickness of the strip. To conduct effective defect analysis, first perform a visual inspection or image analysis on the strip. Use a high-resolution camera or laser scanning device to obtain the surface image of the strip, and then apply image processing algorithms to analyze the image. For example, through edge detection algorithms (such as Canny edge detection or Sobel operator), identify whether there are cracks or irregular shapes on the strip surface. If there are bubbles on the strip surface, the thickness change of the strip can be analyzed to judge. In the presence of bubbles, the thickness of the strip will show obvious fluctuations. In addition, crack detection can also use texture analysis algorithms based on grayscale images to further determine the density, length, and distribution of the cracks on the strip surface. Through these image processing methods, the strip form defect data is extracted, including the defect type, size, distribution, and the severity of the defect.

[0024] Step S22: Derive the abnormal dispensing curing crosslinking density of the defective dispensing execution parameters based on the strip form defect data and the glue raw material data to obtain the strip curing crosslinking density abnormal data; In the embodiments of the present invention, first, it is necessary to deduce the abnormal dispensing execution parameters for defect points according to the data of the strip shape defects and the glue raw material data. In order to understand how the crosslinking density of the strip is affected by the shape defects during the curing process, it is necessary to combine the chemical properties and physical properties of the glue. First, using parameters such as the curing time, crosslinking agent content, and glue viscosity in the glue raw material data, a curing kinetics model is established. This model can be expressed as: , where represents the crosslinking density at time t, is the initial crosslinking density, is the activation energy during the curing process, is the gas constant, is the temperature during curing, is the curing rate constant. By collecting the glue raw material data and environmental conditions (such as temperature, humidity, etc.) in real time, the change in the crosslinking density during the curing process is deduced. Subsequently, according to the strip shape defect data, analyze how these defects affect the crosslinking density of the strip. For example, the presence of cracks and bubbles leads to local failure of the crosslinking reaction, reducing the overall crosslinking density of the strip. In the analysis of strip shape defects, combined with the size and distribution of cracks and bubbles, the abnormal crosslinking density at the defect site is further deduced.

[0025] Step S23: Quantify the lack of interfacial bonding force for the abnormal data of strip curing crosslinking to obtain the quantified data of the lack of interfacial bonding force; In the embodiments of the present invention, the surface science and interfacial mechanics theories are used to further process the abnormal data of curing crosslinking. The specific methods include based on molecular dynamics simulation or classical interfacial mechanics models, combined with the abnormal characteristics of strip curing crosslinking, to quantify the lack of bonding force between the strip and the target surface. Assuming that the interfacial bonding force between the strip and the substrate is mainly composed of van der Waals force, chemical bonding force, and hydrogen bonding force, the following interfacial bonding force formula can be used for modeling: , where is the interfacial bonding force, is a constant related to the material properties, is a coefficient related to the crosslinking degree, is the change in the crosslinking density during the curing process. By fitting the abnormal data of curing crosslinking, combined with various experimental data (such as the surface energy of the strip, curing time, etc.), the lack of interfacial bonding force caused by abnormal crosslinking density during the strip curing process can be quantified. Next, based on the above calculation results, the specific quantified data of the lack of interfacial bonding force will be obtained, reflecting the degree of poor bonding between the strip and the surface due to insufficient or uneven crosslinking density.

[0026] Step S24: Evaluate the weakening degree of the sealing effectiveness based on the abnormal data of the curing crosslinking density of the adhesive strip and the quantified data of the lack of interfacial bonding force, so as to obtain the data of the weakening degree of the sealing effectiveness.

[0027] In the embodiment of the present invention, through the sealing effectiveness weakening evaluation algorithm, combined with the abnormal data of the curing crosslinking density and the quantified data of the lack of interfacial bonding force, the weakening evaluation of the sealing effectiveness is carried out. This evaluation method is based on the principles of adhesive mechanics and fluid mechanics, combines the curing state of the adhesive strip and the bonding force between the adhesive strip and the substrate, and establishes a sealing effectiveness model. According to the classical contact mechanics and sealing theory, the weakening degree of the sealing effectiveness can be described by the following formula: , where S is the sealing effectiveness, F is the interfacial bonding force, A is the contact area, is the sealing effectiveness weakening coefficient. The weakening coefficient is closely related to the curing crosslinking density of the adhesive strip, the degree of lack of interfacial bonding force, and external environmental factors (such as temperature, humidity, etc.). Through the combination of these data, the weakening degree of the sealing effectiveness can be quantified. The evaluation of the weakening degree can be accurately calculated using numerical simulation methods (such as the finite difference method, the finite element method, etc.), so as to obtain the specific value of the weakening of the sealing effectiveness, providing basic data for the subsequent optimization of the dispensing process.

[0028] Step S22 includes the following steps: Step S221: Analyze the crack density of the adhesive strip morphology defect data to obtain the adhesive strip crack density data; Step S222: Evaluate the bubble depth of the adhesive strip morphology defect data to obtain the adhesive strip defect bubble depth data; Step S223: Reverse solve the curing pressure imbalance of the defective dispensing abnormal execution parameters according to the adhesive strip crack density data and the adhesive strip defect bubble depth data to obtain the curing pressure imbalance data; Step S224: Calculate the volume shrinkage ratio of the raw material with curing imbalance based on the glue raw material data and the curing pressure imbalance data to obtain the volume shrinkage ratio of the raw material with curing imbalance; Step S225: Analyze the internal thermal residual stress of the volume shrinkage ratio of the raw material with curing imbalance to obtain the internal thermal residual stress; Step S226: Deduce the abnormal curing crosslinking density of the adhesive strip according to the volume shrinkage ratio of the raw material with curing imbalance and the internal thermal residual stress to obtain the abnormal data of the curing crosslinking density of the adhesive strip.

[0029] In the embodiments of the present invention, first, morphological defect data is obtained from the surface or interior of the rubber strip. The specific method includes using high-precision imaging equipment (such as a scanning electron microscope, a confocal microscope, or an X-ray imaging device) to scan the surface and internal structure of the rubber strip in detail. During this process, image processing algorithms are used to detect and identify cracks on the surface of the rubber strip. The core of image processing is to use image segmentation algorithms, such as the Canny edge detection algorithm, to extract the crack features on the surface of the rubber strip. Through this algorithm, the contour of the crack can be identified, and the complete path of the crack can be formed by connecting the feature points. Then, the connected region analysis method is used to calculate the crack density. The crack density refers to the number of cracks per unit area or the ratio of the total length of the cracks to the surface area of the rubber strip. The calculation formula for the crack density is as follows: C = L / A, where C is the crack density, L is the total length of the cracks, and A is the total surface area of the rubber strip. By scanning and imaging the surface of the rubber strip and combining the length and number of cracks, the crack density data of the rubber strip is obtained. This data provides a basis for the imbalance analysis in the subsequent curing process. First, microscopic imaging technology is used to detect bubbles on the surface or inside the rubber strip. The identification of bubbles mainly relies on image processing technology, especially threshold segmentation and morphological filtering technology based on grayscale images. Threshold segmentation is used to distinguish bubbles from other regions in the image, and morphological filtering can remove noise and enhance the edge features of bubbles. When evaluating the depth of bubbles, the depth of bubbles can be measured by optical tomography technology or three-dimensional imaging equipment. The depth evaluation of bubbles depends on the multi-level slicing and depth information acquisition of the image. Using optical tomography technology (such as OCT), three-dimensional image information of the bubbles inside the rubber strip can be obtained. For each bubble, by calculating its coordinates in three-dimensional space, the depth of the bubble is determined, and the distribution of the bubble depth is obtained through statistical analysis. First, it is necessary to analyze the pressure imbalance during the curing process by using the crack density data and bubble depth data of the rubber strip. The pressure imbalance during the curing process is usually caused by defects such as bubbles and cracks inside the rubber strip, and these defects will affect the curing pressure distribution inside the rubber strip. Therefore, it is necessary to establish a mechanical model based on the defects of the rubber strip to simulate the pressure distribution caused by the defects during the curing process. The finite element analysis (FEA) method can be used to simulate the stress distribution of the rubber strip during the curing process. By inputting the crack density and bubble depth data, a mechanical model of the rubber strip is established, and the uneven pressure distribution caused by the defects during the curing process is calculated. In the model, the curing pressure imbalance can be deduced by the reverse solution method. The core of the reverse solution is to calculate the influence of the known defect data on the pressure during the curing process. First, it is necessary to calculate the volume shrinkage ratio by combining the physical and chemical properties of the glue raw material and the curing pressure imbalance data. The glue raw material will undergo a volume shrinkage phenomenon during the curing process, and the volume shrinkage ratio is an important index for the volume change of the glue raw material during the curing process. The volume shrinkage ratio is usually closely related to the chemical composition, curing rate, and curing temperature of the glue.First, based on the composition data of the glue raw material, using the experimental data or the empirical formula in relevant literature, calculate the theoretical volume shrinkage ratio of the glue during the curing process. A common volume shrinkage ratio calculation formula is: , where β is the volume shrinkage ratio, is the initial volume before curing, is the final volume after curing. By experimentally measuring the initial and final volumes of the glue raw material and combining the known curing pressure imbalance data, calculate the volume shrinkage ratio of the raw material during the curing process. In this calculation process, factors such as the density, molecular structure, and reactivity of the glue raw material need to be considered. Analyze the internal thermal residual stress caused by volume shrinkage during the curing process. The thermal stress caused by volume shrinkage is usually one of the roots of stress imbalance inside the rubber strip during the curing process. Stress analysis can be completed through thermodynamic simulation methods. Specific methods include thermal residual stress analysis based on the finite element method. By inputting factors such as temperature changes, material volume changes, and its thermal expansion coefficient during the curing process into the thermodynamic model, calculate the thermal stress during the curing process. The thermal stress analysis formula is: , where σ is the thermal stress, E is the Young's modulus of the material, α is the thermal expansion coefficient of the material, and ΔT is the temperature change. By calculating the thermal stress generated during the curing process, internal thermal residual stress data can be obtained, which will provide a basis for the subsequent derivation of abnormal curing crosslinking density. By combining the volume shrinkage ratio of the curing imbalance raw material and the internal thermal residual stress data, deduce the abnormal curing crosslinking density of the rubber strip. During the curing process, volume shrinkage and thermal residual stress will affect the crosslinking degree of the rubber strip, thereby leading to abnormal crosslinking density. By establishing a mathematical model and combining the volume shrinkage ratio with the stress field caused by thermal residual stress, obtain the change in the curing crosslinking density of the rubber strip. The abnormal crosslinking density derivation formula is: , where ρc is the curing crosslinking density, ρ0 is the initial crosslinking density, σ is the thermal stress during the curing process, k is the Boltzmann constant, and T is the temperature. Through the derivation of this formula, abnormal crosslinking density data during the curing process of the rubber strip can be obtained, providing a theoretical basis for the subsequent optimization of the dispensing process.

[0030] Step S23 includes the following steps: Step S231: Analyze the viscosity change trend of the abnormal curing crosslinking data of the rubber strip to obtain the viscosity change trend; Step S232: Evaluate the elastic loss gradient of the viscosity change trend to obtain the elastic loss gradient of the rubber strip; Step S233: Conduct interface micro-force field simulation based on the viscosity change trend and the elastic loss gradient of the rubber strip, and perform surface energy contact distribution integration to obtain surface energy contact distribution data; Step S234: Conduct azimuth mean difference multiple regression analysis on the surface energy contact distribution data to obtain contact force azimuth mean difference regression data; Step S235: Quantify the lack of interfacial bonding force based on the regression data of the average difference in the contact force orientation to obtain the quantified data of the lack of interfacial bonding force.

[0031] In the embodiments of the present invention, when analyzing the viscosity change trend, first, viscosity data of the rubber strip at different time points during the curing process are collected. Constant temperature and humidity conditions are set through experiments, and a viscometer is used for measurement. The viscometer can be a rotational viscometer or a cone-plate viscometer. Depending on these devices to provide accurate viscosity values, the time, temperature, and viscosity values are recorded during the measurement process. Subsequently, these data are processed. Through data fitting analysis methods, linear regression or polynomial fitting techniques are adopted to obtain the change trend of viscosity with time. The change rate and trend direction of viscosity with time can be obtained through the fitting curve. According to the data change, the increase or decrease of viscosity during the curing process of the rubber strip is identified, thereby reflecting the stability and quality change of the rubber strip curing. When evaluating the elastic loss gradient, based on the previously obtained viscosity change trend data, the elastic properties of the rubber strip are evaluated using a standard stress-strain curve. The specific steps are to use a dynamic mechanical analyzer (DMA) to measure the storage modulus and loss modulus of the rubber strip at different curing stages. The loss tangent (abbreviated as tanδ) value of the rubber strip is obtained through calculation. This value reflects the degree of energy loss of the rubber strip, and then the elastic loss gradient is evaluated. In implementation, through a temperature sweep experiment, the rubber strip sample is swept from low temperature to high temperature, and the loss modulus value at each temperature is recorded. According to the loss conditions at different temperatures, the elastic loss gradient is calculated, and the elastic loss situation of the rubber strip is obtained based on these data. If the elastic loss gradient increases during the curing process, it indicates that the elastic properties of the rubber strip during the curing process decrease. When performing interface micro-force field simulation, first, based on the viscosity change trend data and elastic loss gradient data, an interface micro-force field model is constructed. This process uses a finite element analysis (FEA) tool. By simulating the stress distribution in different regions during the curing process of the rubber strip, the micro-force field distribution on the surface of the cured rubber strip is obtained. During the simulation, the surface of the rubber strip needs to be divided into multiple grid units, and the force on each unit is calculated through elastic mechanics equations, especially considering the mechanical interaction between the surface of the rubber strip and the contact surface. Through the calculation of surface energy, further surface energy contact distribution integration is performed, and calculations are carried out using finite element software. Through data analysis of the simulation results, the surface energy distribution map of the rubber strip surface contact is obtained, and finally, the surface energy contact distribution data are formed. When performing azimuth mean difference multiple regression analysis, first, the mechanical data of the contact points on the rubber strip surface are extracted from the interface contact simulation results. These data include the magnitude and direction of the contact force in different regions. Using the azimuth mean difference analysis method, the mean difference value of the contact force in each direction is calculated. Through statistics on the direction and magnitude of the contact force of all contact points, the multiple regression analysis method is adopted, and the least squares method is used for data fitting to obtain the regression data of the contact force in each direction. The goal of the regression analysis is to quantify the change trend of the contact force in different directions.Furthermore, the distribution of the interfacial force is judged. Finally, based on the regression data of the azimuth mean difference of the obtained contact force, the missing quantification of the interfacial bonding force of the rubber strip is carried out. Combining the elastic properties and the force field distribution of the rubber strip during the curing process, by combining the total surface energy distribution of the interfacial contact and the regression analysis results, the missing interfacial bonding force caused by uneven cross-linking, bubbles, cracks and other defects during the curing process is determined. The weighted average method is used to quantify the missing amount of the contact force in different regions, and finally the missing data of the interfacial bonding force during the curing process of the rubber strip is obtained. This data can provide a basis for the adjustment of the subsequent dispensing process. Step S3 includes the following steps: Step S31: Normalize the data of the sealing efficiency weakening degree to obtain the normalized data of the sealing efficiency weakening. Step S32: Analyze and resolve the multi-stage curing requirements of the interface according to the normalized data of the sealing efficiency weakening to obtain the multi-stage curing requirement control data of the interface. Step S33: Based on the multi-stage curing requirement control data of the interface, adaptively correct the dispensing process parameters for the defective dispensing abnormality to obtain the adaptively corrected data of the dispensing process. Step S34: Conduct logical learning on the adaptively corrected data of the dispensing process to obtain the adaptively logical corrected data of the dispensing process.

[0032] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: Normalize the data of the sealing efficiency weakening degree to obtain the normalized data of the sealing efficiency weakening. In the embodiment of the present invention, when normalizing the data of the sealing efficiency weakening degree, first, the original data of the sealing efficiency weakening degree is obtained. These data are derived from the above-mentioned quantification result of the missing interfacial bonding force of the rubber strip during the curing process. The data range usually ranges from 0 to 1. However, for unified standardization, the data needs to be converted through a linear normalization method, so that the weakening degree data from different sources and measurement methods can be unified in a standard range, which is convenient for subsequent analysis.

[0033] Step S32: Analyze and resolve the multi-stage curing requirements of the interface according to the normalized data of the sealing efficiency weakening to obtain the multi-stage curing requirement control data of the interface. In the embodiment of the present invention, when performing the analysis of the multi-stage curing requirement control of the interface, it first depends on the normalized data of the weakening of the sealing performance. Using these data, multi-stage control simulations of temperature, pressure, and curing time are carried out on the interface. The specific steps are to divide different curing stages according to the change trend of the normalized data. For example, at the initial stage of curing, lower temperature and pressure are required, while in the middle and late stages, the temperature and pressure need to be gradually increased. The multi-stage linear regression method is used to fit the requirement data of different stages, and the control parameters such as temperature, pressure, and time required for each curing stage are obtained according to the fitting results. At the same time, by analyzing the degree of weakening of the sealing performance, the key control points of each stage are determined to ensure the maximization of the performance during the entire curing process.

[0034] Step S33: Based on the multi-stage curing requirement control data of the interface, perform adaptive correction on the dispensing process parameters of the defective dispensing, so as to obtain the adaptive correction data of the dispensing process; In the embodiment of the present invention, when performing the adaptive correction of the dispensing process based on the multi-stage curing requirement control data of the interface, first transmit the control data to the control system of the dispenser, and perform real-time adjustment on the execution process of the dispenser according to the previously collected dispensing abnormal execution parameters. Specifically, when implementing, use the feedback control algorithm to automatically correct parameters such as the nozzle speed, glue volume, and spraying time of the dispenser. When abnormal situations such as insufficient or excessive glue volume occur, the spraying rate and the moving trajectory of the nozzle are automatically adjusted through the control system to ensure that the glue is evenly coated on the target area. After each correction operation, the quality and distribution of the glue are detected in real time through the monitoring system to form correction data, and finally an optimized dispensing process correction plan is generated. This plan can adaptively adjust the operating state of the dispenser to meet the needs of different products.

[0035] Step S34: Perform logical learning on the adaptive correction data of the dispensing process to obtain the adaptive logical correction data of the dispensing process.

[0036] In the embodiment of the present invention, finally, when performing logical learning on the adaptive correction data of the dispensing process, use the previously generated dispensing process correction data, and establish an adaptive adjustment model of the dispenser through the logical regression analysis method in machine learning. During the model training process, the input variables include the actual effect of each dispensing, the sealing performance of the cured glue strip, the spraying accuracy, etc., and the output target is the corrected dispensing parameters. Through the learning of historical data, the model can be continuously optimized, and finally an adaptive correction logic that can automatically adjust the dispensing process is obtained. When new dispensing process requirements occur, the system will automatically adjust the process parameters according to the patterns in the historical data to achieve intelligent control of the dispensing process. Step S32 includes the following steps: Step S321: Deduce the temperature change sensitivity of the normalized data of weakened sealing effectiveness to obtain the temperature change sensitivity data of weakened sealing; Step S322: Evaluate the expansion / contraction fatigue failure stress based on the temperature change sensitivity data of weakened sealing to obtain the expansion / contraction fatigue failure stress data; Step S323: Identify the non - linear relationship of the temperature change sensitivity data of weakened sealing to generate a weakened - temperature non - linear relationship curve; Calculate the temperature control tolerance of interface contact based on the weakened - temperature non - linear relationship curve to obtain the temperature control tolerance of interface contact; Step S324: Control the temperature change rate of interface contact glue application according to the temperature control tolerance of interface contact and the weakened - temperature non - linear relationship curve to obtain the temperature change rate of interface contact; Step S325: Analyze the multi - stage temperature curing control requirements of the interface according to the temperature control tolerance of interface contact and the temperature change rate of interface contact to obtain the temperature curing requirement control data; Step S326: Analyze the interface pressure curing control requirements based on the expansion / contraction fatigue failure stress data and the temperature curing requirement control data to obtain the pressure curing control requirement data; Step S327: Analyze the multi - stage curing requirement control of the interface according to the temperature curing requirement control data and the pressure curing control requirement data to obtain the multi - stage curing requirement control data of the interface.

[0037] In an embodiment of the present invention, when the temperature change sensitivity of the normalized data of the weakened sealing performance is deduced, the normalized sealing performance weakening data are first obtained. These data reflect the sealing effect of the rubber strip at different curing stages. Then, the sealing performance change curves at different temperatures during the curing process are obtained by measurement or experiment, and these changes are associated with the degree of weakening of the sealing performance. The degree of influence of temperature change on the sealing performance is calculated by differential analysis, and the temperature change sensitivity data of the weakened sealing performance is obtained. Based on these sensitivity data, the specific influence of temperature change on the sealing performance can be deduced, and the degree of weakening under different temperature changes can be further refined. In the specific operation, a temperature simulation experiment is adopted. By continuously adjusting the temperature conditions and measuring its influence on the sealing performance of the rubber strip, the response data of the sealing performance with temperature change are obtained. After deduction, the final sensitivity data are obtained. These data provide a basis for the subsequent expansion / contraction failure stress assessment. When evaluating the expansion / contraction fatigue failure stress based on the seal weakening temperature change sensitivity data, first calculate the temperature-induced expansion or contraction deformation of the rubber strip according to the seal weakening temperature change sensitivity data, and use the stress-strain relationship model in material mechanics to correlate the deformation caused by temperature change with the internal stress of the material. Use the finite element analysis method (FEA) to simulate the stress distribution of the rubber strip under different temperature changes in detail, calculate the fatigue failure stress during the expansion or contraction process, and evaluate the size and distribution of the failure stress, so as to determine the impact of different temperature changes on the long-term performance of the rubber strip, analyze the expansion and contraction effects caused by temperature, and combine the mechanical properties of the material with fatigue failure theory to obtain specific expansion / contraction fatigue failure stress data. These data are helpful to determine the failure risk at the interface. When identifying the nonlinear relationship of the seal weakening temperature change sensitivity data, first use the relationship between temperature and sealing efficiency to establish a nonlinear relationship curve between weakening and temperature through polynomial regression or spline curve fitting and other methods. In the specific operation, a nonlinear regression model is used for fitting, and the change in the degree of weakening of sealing efficiency at different temperatures is calculated. The nonlinear law of sealing efficiency changing with temperature is identified, and the weakening-temperature nonlinear relationship curve is obtained. These curves are then used to calculate the temperature control tolerance. The specific steps are to deduce the interface contact temperature control tolerance under different temperature change conditions based on the fitted relationship curve, analyze the temperature control change range and find the maximum tolerance range allowed for the interface contact point when the temperature changes, and finally obtain the interface contact temperature control tolerance.When controlling the temperature change rate of the interface contact dispensing according to the interface contact temperature control tolerance and the weakening-temperature nonlinear relationship curve, first use the obtained temperature control tolerance data and the nonlinear relationship curve mentioned above. By dynamically adjusting the temperature change rate, determine the most suitable temperature control rate. During specific operations, adopt a speed feedback algorithm to adjust the temperature control rate of the dispensing machine, ensuring that during the dispensing process, the temperature change of the glue strip does not exceed the tolerance range. By real-time detecting the temperature change and weakening data, control the heating element of the dispensing machine to adjust the temperature rising and falling rate, ensuring that the temperature change of the glue strip on the contact surface conforms to the set change rate, and obtain the temperature change rate of the interface contact temperature control. When analyzing the interface multi-stage temperature curing control requirements according to the interface contact temperature control tolerance and the interface contact temperature change rate, first, based on the above calculation results, conduct a temperature control requirement analysis for each stage during the curing process. Divide the curing process into multiple stages. According to the temperature change trend and tolerance limit of each stage, calculate the temperature control requirements for each stage, determine the temperature setting, heating rate, and maintaining time for each stage. Through a multi-stage control model, adjust the temperature change strategy for each stage in real-time to obtain the temperature curing requirement control data, further realizing the precise control of the glue strip curing process. When analyzing the interface pressure curing control requirements based on the expansion / contraction fatigue failure stress data and the temperature curing requirement control data, first combine the expansion / contraction fatigue failure stress data and the temperature curing requirement control data. Through stress-temperature coupling analysis, evaluate the pressure change borne by the interface during the curing process. Combining the compressive performance of the material, analyze the actual performance of the glue strip curing under different pressure conditions. Use the pressure-stress relationship model to calculate the optimal interface pressure control requirements to obtain the pressure curing control requirement data. Further, by adjusting the curing pressure, ensure that the glue strip can receive a uniformly applied pressure during the curing process. When analyzing the interface multi-stage curing requirement control according to the temperature curing requirement control data and the pressure curing requirement control data, based on the obtained temperature and pressure curing requirement data mentioned above, combined with the actual operation situation, further divide the curing process into multiple stages. Through a multi-stage pressure control model, gradually adjust the pressure and temperature changes during the curing process to ensure that each stage meets the predetermined temperature and pressure requirements, and finally obtain the comprehensive interface multi-stage curing requirement control data, ensuring that every detail during the curing process is precisely regulated, thereby improving the dispensing quality and sealing efficiency.

[0038] Step S326 includes the following steps: Perform time-domain fatigue cycle failure stress coupling on the expansion / contraction fatigue failure stress data to obtain fatigue cycle failure stress coupling data; Based on the fatigue cycle failure stress coupling data, perform interface stress distribution difference constraint to obtain interface stress distribution difference constraint data; Adapt the change rate of the distribution constraint pressure according to the interface stress distribution difference constraint data and the temperature curing requirement control data to obtain the change rate of the distribution constraint pressure; Perform multi-stage gradient adaptation of the applied pressure according to the interface stress distribution difference constraint data, the temperature curing requirement control data, and the change rate of the distribution constraint pressure to obtain the multi-stage gradient data of the applied pressure; Analyze the interface pressure curing control requirements based on the change rate of the distribution constraint pressure and the multi-stage gradient data of the applied pressure to obtain the pressure curing control requirement data.

[0039] In the embodiments of the present invention, when performing time-domain fatigue cycle failure stress coupling on the expansion / contraction fatigue failure stress data, first, the expansion / contraction fatigue failure stress data is collected. These data can be obtained by dynamically loading and testing the rubber strips at different curing stages using a high-precision mechanical testing instrument, measuring the influence of expansion and contraction stresses on the rubber strips under different environmental conditions, and obtaining the change of stress cycles during the curing process of the rubber strips through frequency analysis. Using the time-domain analysis method, Fourier Transform is performed on the stress data of each test stage to obtain the stress change law of the rubber strips within different time periods. Further, time-domain coupling analysis is performed on these stress data to correlate the stress cycle characteristics of different curing stages and generate fatigue cycle failure stress coupling data, which reflect the cyclic stress and fatigue damage degree experienced by the rubber strips during the curing process. When performing interface stress distribution difference constraint based on the fatigue cycle failure stress coupling data, first, spatial distribution analysis is performed on the coupling data to obtain the stress distribution at different positions on the rubber strip interface. Using the stress field analysis method, fine modeling of the stress on the surface and interface of the rubber strip is performed to establish a three-dimensional finite element model (Finite Element Model), accurately simulating the geometric shape, material properties, thermal expansion, and pressure loading during the curing process of the rubber strip, calibrating the stress values at each point in the model, and further constraining the stress differences at each point on the interface to ensure that the stress distribution on the entire surface and interface of the rubber strip meets certain uniformity requirements. Through an optimization algorithm, the maximum value of the interface stress difference is calculated, and stress distribution difference constraint data is generated. These data are used for subsequent pressure adaptation and curing control. When performing interface distribution constraint pressure change rate adaptation according to the interface stress distribution difference constraint data and temperature curing requirement control data, first, in combination with the temperature control requirements obtained during the temperature curing process, a physical simulation software is used to model the coupling effect of pressure and temperature. During the simulation process, appropriate material properties and pressure change rate ranges are selected, and using the Stress-Temperature Coupling Model, the interface stress distribution difference constraint is combined with the temperature curing requirements. By simulating the pressure distribution at different temperatures, the pressure change rate is adjusted to ensure that the temperature and pressure changes in each curing stage are within a reasonable range. Specifically, during operation, the temperature and pressure changes in the dispensing area are monitored in real time, and the pressure rate is dynamically adjusted through an adaptive control algorithm to make the pressure change meet the preset change rate requirements, and finally, pressure change rate data that meets the curing requirements is obtained. When performing multi-stage gradient adaptation of the applied pressure according to the interface stress distribution difference constraint data, temperature curing requirement control data, and distribution constraint pressure change rate, first, the pressure change rate data obtained previously is used, combined with the interface stress distribution difference constraint and the curing temperature requirements, to design multiple curing stages, and the pressure is gradually adapted in each stage. The gradient pressure control method is adopted,Gradually increase the pressure value from a lower starting point to a set maximum value, ensuring that the pressure change at each stage meets the requirements of the stress distribution constraint. Use the pressure-time curve model to model the pressure change at each stage, and gradually adjust the pressure gradient at each stage so that the pressure change is smooth and continuous at each stage, ensuring a reasonable stress distribution throughout the curing process. Finally, generate suitable multi-stage gradient data for the applied pressure. These data can ensure that no excessive stress concentration or uneven stress distribution occurs during the curing process of the rubber strip. When analyzing the interface pressure curing control requirements based on the distribution constraint pressure change rate and the multi-stage gradient data of the applied pressure, first comprehensively combine the previously obtained pressure change rate and the multi-stage gradient data of the pressure. Through numerical optimization methods, analyze the pressure requirements of the rubber strip at different stages, determine the optimal pressure and temperature control strategies, and combine the known material parameters to simulate the curing effect under different pressure conditions. Adjust the pressure application method and rate at each stage to ensure that the pressure change during the entire curing process can not only ensure the full curing of the rubber strip but also not cause uneven stress distribution or rubber strip deformation. Use optimization algorithms (such as genetic algorithms or particle swarm optimization) for multi-dimensional optimization, and finally generate pressure curing control requirement data. These data describe the specific pressure requirements at each stage during the entire curing process, ensuring that the stress borne by the rubber strip during the curing process is distributed within a reasonable range and achieving the best curing effect.

[0040] Step S4 includes the following steps: Step S41: Encode the data for self-adaptive logic correction of the dispensing process to obtain the self-adaptive correction code for the dispensing process. Step S42: Based on the self-adaptive correction code for the dispensing process, design an automated firmware to obtain the self-adaptive correction firmware for the dispensing process, and embed the self-adaptive correction firmware for the dispensing process into the control center to perform self-adaptive optimization of the dispenser.

[0041] In the embodiments of the present invention, when encoding the self - adaptive logic correction data of the dispensing process, first, collect and integrate the previously obtained self - adaptive correction data of the dispensing process. These data include the optimization adjustment information of different dispensing parameters during the curing process, such as dispensing speed, glue consumption, dispensing time, etc. By normalizing these data, ensure that their numerical range is suitable for subsequent encoding operations. Then, apply Huffman Encoding or other efficient data compression algorithms to convert these dispensing correction parameters into a set of encoded forms. These encodings can compress and store the data and reduce the computational burden during transmission in the control system. During the encoding process, a combination of fixed - length and variable - length encoding is used to ensure that the encoded data has both a high compression ratio and can guarantee the integrity and accuracy of the decoded data. In this process, identify the correction information in each dispensing process to ensure that each correction step can be uniquely represented by the encoding. Finally, generate the corresponding self - adaptive correction encoding for the dispensing process. This encoding can be transmitted to the control system via a network or storage medium for parsing and execution. When designing the automated firmware based on the self - adaptive correction encoding of the dispensing process, first input the obtained self - adaptive correction encoding of the dispensing process into the firmware development environment. The firmware development environment is an Integrated Development Environment (IDE) that can combine the encoded data with control algorithms to form a control program. During the design process, abstract the control hardware through the Hardware Abstraction Layer (HAL) to ensure that the firmware is compatible with the specific hardware platform. Use programming languages such as C or C++ to implement the development of the automated firmware. The firmware will contain the control algorithms of the dispenser. These algorithms dynamically adjust the various parameters of the dispenser according to the self - adaptive correction encoding, thus realizing the optimization of the dispensing process. Specifically, during operation, through the scheduling module in the firmware, the firmware controls the cooperation between different hardware units, such as the movement of the dispensing head, the ejection of glue, etc., to ensure that in actual operation, the dispenser can adjust the dispensing process in real - time according to the correction encoding. At the same time, through real - time monitoring data, the firmware can continue to optimize the dispensing strategy during the adjustment process. During the design process, it is also necessary to ensure that the firmware can flexibly switch between different operation modes and manage the running state of the firmware through the State Machine model. The finally generated self - adaptive correction firmware for the dispensing process can accurately execute the self - adaptive adjustment task to ensure that the dispensing process meets the set process standards.When embedding the dispensing process adaptive correction firmware into the control center, first select a suitable hardware platform to ensure its compatibility with the firmware. When making the selection, factors such as the computing power of the processor, storage capacity, input / output interfaces, etc. should be considered. Generally, the selected hardware platform includes an embedded control unit and a real-time data acquisition module to ensure that the dispensing machine can operate stably under the control of the firmware. When embedding the firmware, use the firmware burning tool (such as a JTAG programmer) on the hardware platform to burn the developed firmware into the memory of the control center. After the burning is completed, start the control system, and the system automatically loads the firmware and begins to execute the adaptive optimization control task. After the control logic in the firmware parses the dispensing process adaptive correction code, it adjusts the working parameters of the dispensing machine in real time according to the parsing result. The system will regularly perform self-checking and correction through the sensor feedback data to ensure that the firmware can accurately respond to different process requirements. During the entire dispensing process, the control center can also perform real-time monitoring and manual adjustment through the graphical user interface (GUI), and finally complete the adaptive optimization adjustment task of the dispensing machine. After the firmware is successfully embedded, the dispensing machine can continuously adjust the dispensing process according to the real-time monitoring data to meet the requirements of different production environments.

[0042] The present invention also provides an adjustment system for the adaptive optimization of a dispensing machine, which is used to execute the adjustment method for the adaptive optimization of the dispensing machine as described above. The adjustment system for the adaptive optimization of the dispensing machine includes: An abnormal execution parameter mapping module, which is used to obtain the operation log of the dispensing machine; perform mapping of abnormal execution parameters for defective dispensing on the operation log of the dispensing machine to obtain defective dispensing abnormal execution parameters; A sealing efficiency weakening evaluation module, which is used to perform derivation of abnormal curing crosslinking for defective dispensing abnormal execution parameters to obtain abnormal data of glue strip curing crosslinking; perform quantification of the lack of interfacial bonding force on the abnormal data of glue strip curing crosslinking to obtain quantified data of the lack of interfacial bonding force; evaluate the degree of weakening of the sealing efficiency based on the quantified data of the lack of interfacial bonding force to obtain data on the degree of weakening of the sealing efficiency; An adaptive logic correction module, which is used to perform control parsing of the multi-stage curing requirements of the interface according to the data on the degree of weakening of the sealing efficiency to obtain control data for the multi-stage curing requirements of the interface; perform adaptive correction of the dispensing process on the defective dispensing abnormal execution parameters based on the control data for the multi-stage curing requirements of the interface to obtain data on the adaptive logic correction of the dispensing process; An automated firmware design module, which is used to perform automated firmware design based on the data on the adaptive logic correction of the dispensing process to obtain the dispensing process adaptive correction firmware, and embed the dispensing process adaptive correction firmware into the control center to perform the adaptive optimization of the dispensing machine.

[0043] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. An adjustment method for adaptive optimization of a dispensing machine, characterized in that, It includes the following steps: Step S1: Obtain the dispensing machine operation log; perform mapping of dispensing anomaly execution parameters on the dispensing machine operation log to obtain defective dispensing anomaly execution parameters; Step S2: Conduct derivation of dispensing curing crosslinking anomalies on the defective dispensing anomaly execution parameters to obtain glue strip curing crosslinking anomaly data; Quantify the lack of interfacial bonding force for the glue strip curing crosslinking anomaly data to obtain quantified data on the lack of interfacial bonding force; Evaluate the degree of weakening of the sealing efficiency based on the quantified data on the lack of interfacial bonding force to obtain data on the degree of weakening of the sealing efficiency; Step S3: Analyze and resolve the multi-stage curing requirements control for the interface based on the data on the degree of weakening of the sealing efficiency to obtain data on the multi-stage curing requirements control for the interface; Perform adaptive correction of the dispensing process on the defective dispensing anomaly execution parameters based on the data on the multi-stage curing requirements control for the interface to obtain data on the adaptive logic correction of the dispensing process; Step S4: Design an automated firmware based on the data on the adaptive logic correction of the dispensing process to obtain an adaptive correction firmware for the dispensing process, and embed the adaptive correction firmware for the dispensing process into the control center to perform adaptive optimization of the dispensing machine.

2. The adjustment method for adaptive optimization of the dispensing machine according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: Obtain the dispensing machine operation log; Step S12: Extract the historical task execution records from the dispensing machine operation log to obtain historical operation task execution records; Step S13: Extract the glue strip defect status from the historical operation task execution records to obtain the glue strip defect status; Step S14: Perform mapping of dispensing anomaly execution parameters on the dispensing machine operation log according to the glue strip defect status to obtain defective dispensing anomaly execution parameters.

3. The adjustment method for adaptive optimization of the dispensing machine according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Obtain glue raw material data; conduct morphological defect analysis on the glue strip defect status to obtain glue strip morphological defect data; Step S22: Conduct derivation of dispensing curing crosslinking density anomalies on the defective dispensing anomaly execution parameters based on the glue strip morphological defect data and the glue raw material data to obtain glue strip curing crosslinking density anomaly data; Step S23: Quantify the lack of interfacial bonding force for the glue strip curing crosslinking anomaly data to obtain quantified data on the lack of interfacial bonding force; Step S24: Evaluate the degree of weakening of the sealing efficiency based on the glue strip curing crosslinking density anomaly data and the quantified data on the lack of interfacial bonding force to obtain data on the degree of weakening of the sealing efficiency.

4. The adjustment method for adaptive optimization of the dispensing machine according to claim 3, characterized in that Step S22 includes the following steps: Step S221: Conduct crack density analysis on the glue strip morphological defect data to obtain glue strip crack density data; Step S222: Evaluate the bubble depth of the glue strip defect for the glue strip morphological defect data to obtain glue strip defect bubble depth data; Step S223: Perform reverse solution of curing pressure imbalance on the defective dispensing anomaly execution parameters based on the glue strip crack density data and the glue strip defect bubble depth data to obtain curing pressure imbalance data; Step S224: Perform calculation of the raw material volume shrinkage ratio based on the glue raw material data and the curing pressure imbalance data to obtain the volume shrinkage ratio of the cured imbalanced raw material; Step S225: Conduct internal thermal residual stress analysis on the volume shrinkage ratio of the cured imbalanced raw material to obtain internal thermal residual stress; Step S226: Derive the abnormal dispensing curing crosslinking density based on the volume shrinkage ratio and internal thermal residual stress of the cured unbalanced raw materials, and obtain the abnormal data of the cured crosslinking density of the rubber strip.

5. The adjustment method for adaptive optimization of the dispensing machine according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Normalize the data of the weakening degree of the sealing effectiveness to obtain the normalized data of the sealing effectiveness weakening; Step S32: Analyze the multi-stage curing requirements control of the interface based on the normalized data of the sealing effectiveness weakening to obtain the multi-stage curing requirements control data of the interface; Step S33: Perform adaptive correction of the dispensing process on the abnormal execution parameters of the defective dispensing based on the multi-stage curing requirements control data of the interface, so as to obtain the adaptive correction data of the dispensing process; Step S34: Perform logical learning on the adaptive correction data of the dispensing process to obtain the adaptive logical correction data of the dispensing process.

6. The adjustment method for adaptive optimization of the dispensing machine according to claim 5, characterized in that, Step S32 includes the following steps: Step S321: Deduce the temperature change sensitivity of the normalized data of the sealing effectiveness weakening to obtain the temperature change sensitivity data of the sealing weakening; Step S322: Evaluate the stress of expansion / shrinkage fatigue failure based on the temperature change sensitivity data of the sealing weakening to obtain the stress data of expansion / shrinkage fatigue failure; Step S323: Identify the non-linear relationship of the temperature change sensitivity data of the sealing weakening to generate a non-linear relationship curve of weakening-temperature; Calculate the temperature control tolerance of the interface contact based on the non-linear relationship curve of weakening-temperature to obtain the temperature control tolerance of the interface contact; Step S324: Control the temperature change rate of the interface contact dispensing based on the temperature control tolerance of the interface contact and the non-linear relationship curve of weakening-temperature to obtain the temperature change rate of the interface contact; Step S325: Analyze the multi-stage temperature curing control requirements of the interface based on the temperature control tolerance of the interface contact and the temperature change rate of the interface contact to obtain the temperature curing requirements control data; Step S326: Analyze the interface pressure curing control requirements based on the stress data of expansion / shrinkage fatigue failure and the temperature curing requirements control data to obtain the pressure curing control requirements data; Step S327: Analyze the multi-stage curing requirements control of the interface based on the temperature curing requirements control data and the pressure curing control requirements data to obtain the multi-stage curing requirements control data of the interface.

7. The adjustment method for adaptive optimization of the dispensing machine according to claim 1, wherein, Step S4 includes the following steps: Step S41: Perform coding processing on the adaptive logical correction data of the dispensing process to obtain the adaptive correction code of the dispensing process; Step S42: Design the automation firmware based on the adaptive correction code of the dispensing process to obtain the adaptive correction firmware of the dispensing process, and embed the adaptive correction firmware of the dispensing process into the control center to perform the adaptive optimization of the dispensing machine.

8. An adjustment system for adaptive optimization of a dispensing machine, characterized in that, An adjustment method for performing the adaptive optimization of the dispensing machine as described in claim 1, the adjustment system for the adaptive optimization of the dispensing machine includes: An abnormal execution parameter mapping module, configured to obtain the operation log of the dispensing machine; perform mapping of the abnormal execution parameters of the dispensing on the operation log of the dispensing machine to obtain the abnormal execution parameters of the defective dispensing; A sealing efficiency weakening evaluation module is used to deduce the abnormal dispensing curing crosslinking of the defective dispensing abnormal execution parameters to obtain the glue strip curing crosslinking abnormal data; quantify the lack of interfacial bonding force for the glue strip curing crosslinking abnormal data to obtain the interfacial bonding force lack quantification data; evaluate the sealing efficiency weakening degree based on the interfacial bonding force lack quantification data to obtain the sealing efficiency weakening degree data; An adaptive logic correction module is used to analyze the interfacial multi-stage curing requirement control according to the sealing efficiency weakening degree data to obtain the interfacial multi-stage curing requirement control data; perform the dispensing process adaptive correction on the defective dispensing abnormal execution parameters based on the interfacial multi-stage curing requirement control data to obtain the dispensing process adaptive logic correction data; An automated firmware design module is used to perform automated firmware design based on the dispensing process adaptive logic correction data to obtain the dispensing process adaptive correction firmware, and embed the dispensing process adaptive correction firmware into the control center to perform the dispensing machine adaptive optimization.

Images