Automatic packaging test method and system for micro-fluidic chip

Abstract

The invention relates to the field of chip packaging testing, in particular to an automatic packaging testing method and system for a micro-fluidic chip. The method comprises the following steps: acquiring a real-time monitoring image of a micro-fluidic chip to be packaged in a packaging box; performing chip position alignment calibration processing on the real-time monitoring image of the micro-fluidic chip, and collecting a calibrated chip monitoring image; performing chip internal component visual inspection and multi-channel flow topological correlation fitting on the calibrated chip monitoring image, and constructing a chip packaging micro-channel topological structure model; and obtaining a packaging demand log, performing automatic packaging and filling execution on the chip packaging micro-channel topological structure model, and collecting environment monitoring parameters of the microfluidic packaging box. The packaging technology is continuously optimized through real-time feedback, the packaging test parameters are automatically adjusted, and the stability and precision of the packaging technology are gradually improved.

Description

Technical Field

[0001] The present invention relates to the field of chip packaging and testing, and in particular to an automatic packaging and testing method and system for a microfluidic chip. Background Art

[0002] Microfluidic chips are devices that can accurately control the flow of liquids at the micron scale and are widely used in biomedicine, environmental monitoring, chemical analysis and other fields. With the development of microfluidic technology, the integration, functional complexity and application fields of microfluidic chips are constantly expanding, requiring higher requirements for chip packaging and testing accuracy. Packaging is a crucial link in the manufacturing process of microfluidic chips, which is directly related to the performance and service life of the chip. Traditional microfluidic chip packaging and testing methods mainly rely on manual operation or semi-automatic equipment. The testing process is cumbersome and there are certain manual errors, which not only affects the efficiency of the test, but may also lead to unstable packaging quality, thereby affecting the final performance of the microfluidic chip.

[0003] During long-term use, microfluidic chip packaging may be affected by many factors, such as aging of packaging materials, poor sealing, unstable connection interfaces, etc., which may lead to problems such as fluid leakage, channel blockage, and detection errors. In order to ensure the packaging quality and test accuracy of microfluidic chips, traditional testing methods often rely on manual inspection or single functional testing, and cannot conduct comprehensive and accurate packaging quality assessment of a large number of chips in a short period of time. With the widespread promotion of microfluidic chip applications, especially in the fields of life sciences and precision medicine, the limitations of traditional packaging and testing methods are becoming increasingly apparent, and there is an urgent need for an efficient, accurate, and intelligent microfluidic chip packaging and testing method.

[0004] Therefore, developing an automated microfluidic chip packaging testing method that can efficiently and accurately complete chip packaging quality inspection and improve test efficiency and accuracy is of great significance for meeting the needs of large-scale production and quality control of modern microfluidic chips. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes an automated packaging and testing method and system for a microfluidic chip to solve at least one of the above technical problems.

[0006] To achieve the above object, the present invention provides an automated packaging and testing method for a microfluidic chip, comprising the following steps: Step S1: obtaining a real-time monitoring image of a microfluidic chip to be packaged in a packaging box; performing chip position alignment and calibration processing on the real-time monitoring image of the microfluidic chip, and collecting the calibrated chip monitoring image; Step S2: performing visual inspection of chip internal components and multi-channel flow topology correlation fitting on the calibrated chip monitoring image to construct a chip packaging microchannel topology structure model; Step S3: Obtaining the packaging demand log, and automatically performing packaging filling on the chip packaging microfluidic channel topology model, and collecting environmental monitoring parameters of the microfluidic packaging box; Step S4: performing dynamic packaging parameter deviation calculation on the environmental monitoring parameters of the microfluidic packaging box, and performing real-time environmental parameter adjustment, thereby constructing a real-time packaging box parameter adjustment strategy; Step S5: obtaining a chip monitoring image after microfluidic packaging is completed, and performing a comprehensive packaging quality assessment to obtain a packaging quality assessment report; Step S6: Perform chip packaging quality diagnosis for each chip according to the packaging quality assessment report, perform self-learning iterative optimization according to the real-time packaging box parameter adjustment strategy, and build an automated packaging test optimization model.

[0007] The present invention can ensure the precise positioning of the chip on the packaging platform by acquiring the real-time monitoring image of the microfluidic chip and performing position alignment calibration, thereby avoiding uneven packaging or functional failure caused by chip deviation. Automated position alignment calibration reduces the need for manual intervention, reduces the occurrence of human errors, and improves the consistency and repeatability of the overall packaging process. Accurate chip positioning means that subsequent packaging steps can be carried out more smoothly, avoiding rework caused by position deviation, and greatly improving production efficiency. Visual inspection of the internal components of the chip can identify the microstructure of the microfluidic chip, such as important components such as flow channels, inlets, and outlets. Through multi-channel flow topology correlation fitting, the microchannel topology structure model of the chip can be accurately established to provide detailed structural information for subsequent packaging processes. Through accurate modeling of the microfluidic chip, the flow path and filling method of the packaging material can be optimized, the packaging quality can be improved, and the closure and uniformity of the microchannel can be ensured. Multi-channel flow topology correlation fitting helps to avoid flow conflicts or interferences between different microchannels in the chip, ensuring the functionality and work efficiency of each channel. According to the packaging demand log and the topological structure of the microfluidic chip, the system can accurately perform automated packaging filling to ensure that each microchannel can obtain uniform and sufficient packaging materials. Automated filling execution can reduce manual intervention, significantly improve production speed and consistency, and reduce defects caused by human errors in the packaging process. During the packaging process, real-time collection of environmental monitoring parameters (such as temperature, humidity, pressure, etc.) in the packaging box provides data support for the next step of packaging quality evaluation and adjustment to ensure that the packaging environment is always in the optimal state. Dynamic deviation calculation and instant adjustment of the environmental parameters of the packaging box can ensure that environmental factors such as temperature and pressure are always in the optimal range of the packaging process, avoiding packaging defects caused by environmental fluctuations. By correcting the parameter deviation in the packaging process in real time, the stability of the packaging environment can be ensured, thereby improving the stability and long-term reliability of the packaging. Real-time adjustment of environmental parameters can minimize packaging defects caused by environmental factors, thereby reducing the defective rate in the production process. By conducting a comprehensive quality assessment of the chip after packaging, the system can accurately detect packaging defects, microchannel sealing problems, and uneven material distribution, and generate a detailed quality assessment report. The packaging quality assessment report can provide the specific location and type of packaging defects, so that production personnel can make targeted corrections or optimizations in the subsequent steps. By generating a detailed packaging quality report, it is easy to trace the packaging process and quality of each batch of chips, ensure the transparency and standardization of the production process, and improve the level of product quality control. Based on the packaging quality assessment report, quality diagnosis of each chip can quickly locate problems in the packaging and carry out targeted processing, which helps to improve the production qualification rate of chips.By using the real-time packaging box parameter adjustment strategy for self-learning, the system can continuously optimize the packaging process based on historical data and real-time feedback, automatically adjust the packaging test parameters, avoid errors caused by human factors, and gradually improve the stability and accuracy of the packaging process. Through the continuous updating and iteration of the automated packaging test optimization model, the packaging process can be continuously improved, production efficiency and chip packaging quality can be further improved, and the packaging requirements of different types of microfluidic chips can be met.

[0008] In this specification, an automated packaging and testing system for a microfluidic chip is provided, which is used to perform the automated packaging and testing method for the microfluidic chip as described above, comprising: A position calibration module is used to obtain a real-time monitoring image of a microfluidic chip to be packaged in a packaging box; perform chip position alignment and calibration processing on the real-time monitoring image of the microfluidic chip, and collect the calibrated chip monitoring image; A microfluidic channel topology module is used to perform visual inspection of chip internal components and multi-channel flow topology correlation fitting on the calibrated chip monitoring image to construct a chip packaging microfluidic channel topology structure model; The packaging and filling execution module is used to obtain the packaging demand log, and automatically execute the packaging and filling of the chip packaging microfluidic topology model, and collect the environmental monitoring parameters of the microfluidic packaging box; An immediate adjustment module is used to perform dynamic packaging parameter deviation calculation on the environmental monitoring parameters of the microfluidic packaging box and perform immediate environmental parameter adjustment, thereby constructing an immediate packaging box parameter adjustment strategy; The quality assessment module is used to obtain chip monitoring images after microfluidic packaging is completed, and to conduct a comprehensive packaging quality assessment to obtain a packaging quality assessment report; The iterative optimization module is used to diagnose the packaging quality of each chip according to the packaging quality assessment report, and to perform self-learning iterative optimization according to the real-time packaging box parameter adjustment strategy to build an automated packaging test optimization model.

[0009] The present invention uses a high-resolution camera to perform real-time image acquisition on the microfluidic chip, and can accurately obtain the current position, size and shape of the chip. This can provide the most accurate basic data for subsequent packaging operations. The automatic alignment and calibration of the chip not only eliminates the deviation in manual operation, but also greatly improves the accuracy of the packaging process. Accurate alignment can avoid the position offset of the chip during the packaging process, ensure the consistency of the chip packaging position and shape, and reduce the possibility of packaging failure. Through the calibrated image, accurate image data is further provided for the internal structure analysis and packaging test of the chip, and important prerequisite data is provided for subsequent steps (such as flow topology analysis and packaging process). Computer vision technology is used to automatically identify and mark all key components inside the chip (such as microfluidic channels, holes, valves, etc.). This not only improves the accuracy of detection, but also avoids omissions and errors in manual detection. By fitting the multi-channel flow topology in the microfluidic chip, a topological structure model of the microchannel can be constructed. This model can accurately describe the fluid transmission path in the chip, which helps to optimize fluid control, flow regulation and material distribution in the packaging process. Through the accurate flow topology model, the flow pattern of the fluid in the chip after packaging can be effectively predicted, providing a theoretical basis for the subsequent packaging filling process, ensuring that the fluid is not blocked or bubbled during the filling process. The packaging parameters are automatically obtained according to the packaging demand log, avoiding the inconsistency in manual intervention, and adjusting the filling flow rate, pressure, temperature and other parameters according to actual needs. Through precise automatic filling control, the microfluidic channel can accurately fill the required materials to ensure that the fluid filling of each channel is uniform, avoiding errors and inconsistencies in manual operation. Real-time collection of environmental parameters (such as temperature, humidity, pressure, etc.) in the packaging box provides real-time data support for subsequent packaging quality analysis and optimization. This step ensures that the environmental factors in the packaging process are always in the optimal state. Through real-time analysis of the environmental monitoring data of the packaging box, the deviation of environmental factors such as temperature and pressure can be quickly identified and adjusted in time. This greatly reduces the instability caused by fluctuations in environmental factors during the packaging process. Dynamic deviation calculation and instant adjustment strategy ensure that the environmental parameters are always kept within the optimal range, avoiding inappropriate temperature or pressure fluctuations affecting the packaging quality. The stability of the packaging process is guaranteed, especially in long-term packaging operations. Adjusting the packaging environment in real time can ensure that all chips are under the same environmental conditions during the packaging process, enhancing the consistency and reliability of the packaging process and reducing the packaging defect rate. The chip monitoring image after packaging can provide detailed chip packaging status. Comprehensive evaluation can comprehensively analyze the integrity, sealing and material distribution of chip packaging to ensure high quality packaging. Through automatic image analysis, small defects generated during the packaging process, such as bubbles, cracks, and uneven materials, can be identified. If these defects are not discovered in time, they may lead to subsequent poor functions or failures, so it is very important to discover and repair them in time.The packaging quality assessment report provides data support for the improvement of the packaging process, which is helpful for subsequent packaging optimization and quality control. The packaging quality of each chip can be diagnosed individually to ensure that each chip meets the packaging standards. Unqualified chips are marked and the problems are located to avoid putting unqualified chips into the next stage. Based on real-time feedback data, the system can self-learn and optimize various parameters in the packaging process (such as temperature, pressure, filling rate, etc.) to continuously improve the packaging quality. Through data accumulation and analysis, the automated packaging test optimization model is gradually improved. The model can adjust process parameters based on historical packaging data, thereby optimizing future packaging processes and improving overall packaging efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic flow chart of the steps of an automated packaging and testing method for a microfluidic chip according to the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0011] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0012] The present application example provides an automated packaging and testing method and system for a microfluidic chip. The execution subject of the automated packaging and testing method and system for a microfluidic chip includes but is not limited to: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as a general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0013] See also Figures 1 to 4 The present invention provides an automated packaging and testing method for a microfluidic chip, the automated packaging and testing method for a microfluidic chip comprising the following steps: Step S1: obtaining a real-time monitoring image of a microfluidic chip to be packaged in a packaging box; performing chip position alignment and calibration processing on the real-time monitoring image of the microfluidic chip, and collecting the calibrated chip monitoring image; Step S2: performing visual inspection of chip internal components and multi-channel flow topology correlation fitting on the calibrated chip monitoring image to construct a chip packaging microchannel topology structure model; Step S3: Obtaining the packaging demand log, and automatically performing packaging filling on the chip packaging microfluidic channel topology model, and collecting environmental monitoring parameters of the microfluidic packaging box; Step S4: performing dynamic packaging parameter deviation calculation on the environmental monitoring parameters of the microfluidic packaging box, and performing real-time environmental parameter adjustment, thereby constructing a real-time packaging box parameter adjustment strategy; Step S5: obtaining a chip monitoring image after microfluidic packaging is completed, and performing a comprehensive packaging quality assessment to obtain a packaging quality assessment report; Step S6: Perform chip packaging quality diagnosis for each chip according to the packaging quality assessment report, perform self-learning iterative optimization according to the real-time packaging box parameter adjustment strategy, and build an automated packaging test optimization model.

[0014] The present invention can ensure the precise positioning of the chip on the packaging platform by acquiring the real-time monitoring image of the microfluidic chip and performing position alignment calibration, thereby avoiding uneven packaging or functional failure caused by chip deviation. Automated position alignment calibration reduces the need for manual intervention, reduces the occurrence of human errors, and improves the consistency and repeatability of the overall packaging process. Accurate chip positioning means that subsequent packaging steps can be carried out more smoothly, avoiding rework caused by position deviation, and greatly improving production efficiency. Visual inspection of the internal components of the chip can identify the microstructure of the microfluidic chip, such as important components such as flow channels, inlets, and outlets. Through multi-channel flow topology correlation fitting, the microchannel topology structure model of the chip can be accurately established to provide detailed structural information for subsequent packaging processes. Through accurate modeling of the microfluidic chip, the flow path and filling method of the packaging material can be optimized, the packaging quality can be improved, and the closure and uniformity of the microchannel can be ensured. Multi-channel flow topology correlation fitting helps to avoid flow conflicts or interferences between different microchannels in the chip, ensuring the functionality and work efficiency of each channel. According to the packaging demand log and the topological structure of the microfluidic chip, the system can accurately perform automated packaging filling to ensure that each microchannel can obtain uniform and sufficient packaging materials. Automated filling execution can reduce manual intervention, significantly improve production speed and consistency, and reduce defects caused by human errors in the packaging process. During the packaging process, real-time collection of environmental monitoring parameters (such as temperature, humidity, pressure, etc.) in the packaging box provides data support for the next step of packaging quality evaluation and adjustment to ensure that the packaging environment is always in the optimal state. Dynamic deviation calculation and instant adjustment of the environmental parameters of the packaging box can ensure that environmental factors such as temperature and pressure are always in the optimal range of the packaging process, avoiding packaging defects caused by environmental fluctuations. By correcting the parameter deviation in the packaging process in real time, the stability of the packaging environment can be ensured, thereby improving the stability and long-term reliability of the packaging. Real-time adjustment of environmental parameters can minimize packaging defects caused by environmental factors, thereby reducing the defective rate in the production process. By conducting a comprehensive quality assessment of the chip after packaging, the system can accurately detect packaging defects, microchannel sealing problems, and uneven material distribution, and generate a detailed quality assessment report. The packaging quality assessment report can provide the specific location and type of packaging defects, so that production personnel can make targeted corrections or optimizations in the subsequent steps. By generating a detailed packaging quality report, it is easy to trace the packaging process and quality of each batch of chips, ensure the transparency and standardization of the production process, and improve the level of product quality control. Based on the packaging quality assessment report, quality diagnosis of each chip can quickly locate problems in the packaging and carry out targeted processing, which helps to improve the production qualification rate of chips.By using the real-time packaging box parameter adjustment strategy for self-learning, the system can continuously optimize the packaging process based on historical data and real-time feedback, automatically adjust the packaging test parameters, avoid errors caused by human factors, and gradually improve the stability and accuracy of the packaging process. Through the continuous updating and iteration of the automated packaging test optimization model, the packaging process can be continuously improved, production efficiency and chip packaging quality can be further improved, and the packaging requirements of different types of microfluidic chips can be met.

[0015] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of an automated packaging and testing method for a microfluidic chip of the present invention. In this example, the steps of the automated packaging and testing method for a microfluidic chip include: Step S1: obtaining a real-time monitoring image of a microfluidic chip to be packaged in a packaging box; performing chip position alignment and calibration processing on the real-time monitoring image of the microfluidic chip, and collecting the calibrated chip monitoring image; In this embodiment, a high-resolution microscope or industrial camera is installed in the packaging box, which can capture images of the microfluidic chip in real time. These devices should have good optical properties to ensure image quality. Configure a suitable light source (such as an LED light) to avoid shadows and reflections, and ensure that the details of the chip surface and microchannels are clearly visible. Generally, the light source should be set at an appropriate distance from the shooting angle to obtain a uniform lighting effect. Start the monitoring system and set the frequency of image acquisition. Usually, one frame of image is acquired per second to observe the chip status in real time. During the acquisition process, ensure that the equipment remains stable to avoid any possible vibration that affects the image quality. Perform multiple image acquisitions to ensure that different viewing angles and states of the chip can be captured. Record the acquisition time, position and other relevant parameters of each image for subsequent analysis and processing. After the acquisition is completed, check the clarity and integrity of all images, and remove blurred or out-of-focus images to ensure the accuracy of subsequent processing. Store qualified images in a database, ensuring that each image is marked with a timestamp and relevant parameters for subsequent positioning and calibration analysis. Input the acquired real-time monitoring images into image processing software (such as ImageJ or OpenCV) for preprocessing, including noise removal and contrast enhancement. This step helps improve the overall quality of the image and makes the features of the microfluidic chip more prominent. Use filters (such as Gaussian filtering) to smooth the image and reduce background noise, ensuring that the edges and features of the chip can be more accurately identified in the subsequent alignment and calibration process. Use feature matching technology to align the chip position. First, identify key feature points in the image, such as the four corners of the chip or specific markers. You can use SIFT (Scale Invariant Feature Transform) or SURF (Speeded Robust Features) algorithms for feature extraction. Match the extracted feature points with predefined standard positions and calculate the rotation, translation, and scaling parameters of the chip. Ensure that the position of the chip in the image is consistent with the actual position. According to the calculated alignment parameters, transform the original image to generate a calibrated chip monitoring image. Use affine transformation or perspective transformation algorithms to ensure that the position and scale of the chip in the image are accurate. Save the calibrated image and record the alignment parameters used for subsequent quality monitoring and analysis. These parameters will be used in the subsequent packaging process to ensure that the chip maintains the correct position during the packaging process.

[0016] Step S2: performing visual inspection of chip internal components and multi-channel flow topology correlation fitting on the calibrated chip monitoring image to construct a chip packaging microchannel topology structure model; In this embodiment, the calibrated chip monitoring image is extracted from the database to ensure that the image is clear and has sufficient resolution so that the internal components can be effectively identified. High-resolution images are usually selected, at least 2000x2000 pixels, so that the details are clear. Select suitable image processing software (such as ImageJ or OpenCV) and import the image for subsequent analysis. These software provide a variety of image processing tools that can help identify and extract features. Edge detection is performed in the image, and the contours of the internal components of the chip are extracted using the Canny edge detection algorithm. The algorithm can effectively identify the edges of the components and ignore background noise. Combined with morphological operations (such as expansion and corrosion), the edges are further clarified to ensure that the contours of the internal components are complete and continuous. Through processing, the key features of the components (such as pumps, valves, and channels) are highlighted. The detected components are marked and the type, position, and size of each component are recorded. A template matching algorithm can be used to identify specific component shapes and compare them with a predefined component database. Generate a component detection report to record the parameter information of each component, including its coordinates, size, and shape features in the image. These data provide a basis for subsequent flow topology analysis. Draw a preliminary channel connection diagram based on the identified component information and its position in the chip. Use CAD software or custom tools to input the connection relationship between components and channels to generate a preliminary geometric model of the microfluidic channel. Determine the geometric characteristics of each channel, including length, width, angle and connection method. These characteristics are crucial for subsequent flow analysis. Use fluid dynamics simulation tools (such as CFD software) to perform flow analysis on the constructed microfluidic channel topology. Input the physical properties of the fluid (such as viscosity, density) and flow conditions (such as inlet flow rate) to simulate the flow behavior of the fluid in the microfluidic channel. Perform multi-channel flow correlation fitting, monitor the flow velocity distribution and pressure changes of the fluid in different channels, and identify possible flow bottlenecks or uneven phenomena. According to the simulation results and topological structure analysis, optimize the design of the microfluidic channel to ensure the rationality of the flow path. Adjust the shape and connection method of the channel to improve flow efficiency and reduce flow resistance. Generate the final microfluidic channel topology model and record the model parameters and flow characteristics. Ensure the integrity of the data for subsequent packaging process and performance evaluation.

[0017] Step S3: Obtaining the packaging demand log, and automatically performing packaging filling on the chip packaging microfluidic channel topology model, and collecting environmental monitoring parameters of the microfluidic packaging box; In this embodiment, the packaging requirement log is extracted from the project management system to ensure that the log contains all relevant packaging parameters and requirements. These parameters typically include the required packaging material type, filling pressure, filling speed, ambient temperature and humidity, etc. Review the log content to ensure the integrity and accuracy of the information. Pay special attention to specific requirements related to microfluidic chips, such as fluid properties and geometric characteristics of microchannels, to ensure the smooth progress of the subsequent filling process. Perform a detailed analysis of the obtained packaging requirements and extract key parameters. For example, determine the required filling material (such as epoxy resin or polymer), target filling pressure (usually between 100kPa and 300kPa), and filling speed (such as 50 microliters per minute). Sort out personalized packaging requirements for different chip designs, including filling requirements for each microchannel and expected packaging environmental conditions. This information will provide guidance for subsequent automated packaging settings. Configure automated packaging equipment to ensure that it has the ability to accurately control filling pressure and flow rate. The equipment should be able to automatically adjust according to the parameters in the packaging requirement log, setting the filling pressure and filling speed to the required values. Perform pre-inspection and calibration of the equipment to ensure that all sensors and actuators are working properly and can be monitored and adjusted in real time during the filling process. Start the automated filling program, and the device will automatically fill the microchannels according to the set packaging parameters. During the filling process, monitor the pressure and flow rate in real time to ensure that they meet the preset conditions. Monitor the fluid behavior during the filling process to ensure that the fluid can smoothly fill all microchannels and avoid bubbles or blockages. Record key parameters in the filling process, such as filling time, flow rate changes, and pressure fluctuations. After the filling is completed, save the data during the filling process, including information such as pressure, flow rate, and filling time. Ensure the integrity of the data for subsequent analysis and quality assessment. Perform a preliminary assessment of the filling effect to check whether there is uneven filling or excessive flow resistance, so as to adjust the packaging strategy in time. During the packaging process, configure the environmental monitoring system, including temperature sensors, humidity sensors, and pressure sensors, to ensure that the environmental conditions in the packaging box can be monitored in real time. These sensors should have high sensitivity and fast response capabilities to capture environmental changes in time. Set the acquisition frequency of the monitoring system, usually once per second, to record the changes in environmental parameters in detail. Start the environmental monitoring system and start collecting temperature, humidity, and pressure data in the packaging box in real time. Ensure that the system runs stably and accurately record the values ​​read each time. The collected data is analyzed in real time, and attention is paid to whether the environmental parameters are within the preset range. For example, the temperature should be maintained between 20°C and 25°C, and the relative humidity should be controlled between 30% and 50% to ensure the stability of the packaging process.

[0018] Step S4: performing dynamic packaging parameter deviation calculation on the environmental monitoring parameters of the microfluidic packaging box, and performing real-time environmental parameter adjustment, thereby constructing a real-time packaging box parameter adjustment strategy; In this embodiment, real-time collected environmental parameter data, including temperature, humidity and pressure, are obtained from the environmental monitoring system. These data should include all time points in the packaging process for comprehensive analysis. At the same time, the target parameters in the packaging demand log are collected, such as the target temperature should be maintained at 22°C, the humidity should be controlled at 40%, and the pressure should be maintained at 100kPa. These target parameters will be used as a benchmark for subsequent deviation calculations. The real-time monitoring data is compared with the target parameters to calculate the deviation value of each environmental parameter. For example, if the real-time temperature is 24°C and the target temperature is 22°C, the deviation is +2°C. The same method applies to humidity and pressure. The calculated deviation values ​​are organized into a table, and the deviation at each time point is recorded so as to respond promptly to changes in environmental parameters. Statistical analysis tools (such as time series analysis) are used to dynamically analyze the deviation data to identify the trend of parameter changes. For example, if the temperature continues to rise, it may indicate that heat is accumulated in the packaging box and measures need to be taken to adjust it. The frequency and amplitude of the deviation changes are recorded so that the subsequent immediate adjustment strategy can be targeted to deal with possible environmental fluctuations. According to the results of the deviation calculation, an immediate environmental parameter adjustment strategy is formulated. For example, if the monitored temperature is too high, the strategy may include increasing the cooling function of the packaging box or adjusting the temperature of the working environment. Ensure that the adjustment strategy is flexible and can respond dynamically according to the changes in the real-time monitoring data. For example, set a threshold to immediately trigger the cooling system when the temperature deviation exceeds ±1°C. Start the automated control system to make instant adjustments to the environmental parameters according to the established adjustment strategy. For example, if the temperature exceeds the set range, automatically adjust the power of the cooling system to reduce the temperature. Monitor the adjustment process to ensure that each environmental parameter can quickly return to the target range. During the adjustment process, record parameter changes in real time for subsequent analysis. Evaluate the effect of the adjustment and monitor the changes in the environmental parameters after the adjustment to ensure that they return to the target value. If the temperature does not drop effectively after the adjustment, further analyze the cause and adjust the strategy. Based on the results of the effect evaluation, optimize the adjustment strategy to ensure that the fluctuations of environmental parameters can be responded to more quickly and accurately in future packaging processes. For example, if the cooling system does not respond quickly enough, consider increasing its power or adjusting the control logic. Integrate the results of deviation calculation, instant adjustment, and effect evaluation to form a complete set of instant environmental parameter adjustment strategy documents. Ensure that the target value, tolerance range and corresponding adjustment measures for each environmental parameter are listed in detail in the document. Include specific operating procedures and emergency plans in the document so that operators can quickly refer to and implement adjustments when encountering similar situations in the future. Train relevant operators to make them familiar with the content and implementation methods of the real-time packaging box parameter adjustment strategy. Ensure that the team can flexibly apply these strategies in actual operations. During the actual packaging process, continuously monitor environmental parameters and dynamically adjust them according to the strategy to ensure the stability and quality of the packaging process.Establish a continuous optimization feedback mechanism and regularly evaluate the effectiveness of the adjustment strategy. According to the feedback information in the actual packaging process, gradually optimize the strategy content to adapt to different packaging requirements and environmental changes. Record the results and lessons learned from each adjustment to form a knowledge base to provide reference and guidance for the subsequent packaging process.

[0019] Step S5: obtaining a chip monitoring image after microfluidic packaging is completed, and performing a comprehensive packaging quality assessment to obtain a packaging quality assessment report; In this embodiment, after the microfluidic encapsulation is completed, a high-resolution microscope or industrial camera is configured to ensure that the device can accurately capture the image of the encapsulated chip. The device should have autofocus and image stabilization functions to ensure that the image is clear and blur-free. Ensure that the light source is set reasonably, usually a white light LED light source is selected to avoid reflections and shadows, and ensure that the details of the chip can be clearly displayed when shooting. Place the encapsulated microfluidic chip under a microscope, adjust the focal length and viewing angle to ensure that all parts of the chip can be fully photographed, including microchannels, interfaces, and package edges. Start the image acquisition system and set it to capture one frame of image per second. It is recommended to collect multiple images and shoot from different angles and positions to cover all key areas of the chip. After the acquisition is completed, check the quality of the image to ensure that all images are clear and usable, and remove blurred or out-of-focus images. Record the acquisition time and shooting parameters of each image for subsequent analysis. Store qualified images in the database and mark them to ensure subsequent traceability. Preprocess the acquired chip monitoring images, including denoising and improving contrast. This can be achieved by using Gaussian filters and histogram equalization techniques to ensure that details are more obvious in subsequent analysis. Ensure that the format and resolution of the image are suitable for subsequent analysis. Usually, PNG or TIFF formats are selected to maintain image quality. Determine the key indicators for package quality assessment, including package integrity, sealing, material distribution uniformity, and defect detection. These indicators will be used to quantify the quality of the package. Establish evaluation criteria, for example, the sealing score should reach more than 90 points, and the material distribution uniformity should be within the set standard range. Use image processing software to analyze the image, apply edge detection and feature recognition algorithms, and identify the key areas of the chip and possible defects (such as bubbles, cracks, etc.). Calculate the value of each evaluation indicator, record the number and type of defects detected, and score according to the set standards. For example, if 3 bubbles are detected, the sealing score will be deducted accordingly. Organize the evaluation results into a report, including the specific value of each indicator, description of the defect, image examples, and comprehensive evaluation conclusions. Ensure that the report structure is clear and easy for relevant personnel to understand. The report should also include improvement suggestions to facilitate subsequent packaging process optimization. Document factors that may affect package quality, such as environmental conditions or device performance, to allow for future adjustments.

[0020] Step S6: Perform chip packaging quality diagnosis for each chip according to the packaging quality assessment report, perform self-learning iterative optimization according to the real-time packaging box parameter adjustment strategy, and build an automated packaging test optimization model.

[0021] In this embodiment, key information is extracted from the packaging quality assessment report, with special attention paid to the packaging quality score of each chip and the type of defects detected. Ensure a clear understanding of the specific quality issues of each chip and their impact. Develop a systematic diagnostic table to organize the identification, quality score, defect description and influencing factors of each chip for subsequent analysis and decision-making. Analyze each chip one by one, focusing on chips with scores below a set threshold (such as 80 points). Use statistical analysis methods (such as standard deviation and mean analysis) to evaluate the quality performance of each chip. For each unqualified chip, record its defect type, frequency of occurrence and possible causes in detail. For example, if multiple chips have bubble defects, it is necessary to analyze whether it is related to the selection of packaging materials, filling pressure or environmental conditions. Combined with the real-time packaging box parameter adjustment strategy, identify the key factors that may cause quality problems. Use tools such as fault tree analysis (FTA) or fishbone diagrams (cause and effect diagrams) to systematically analyze the root causes of defects. Record the analysis results and form preliminary improvement suggestions to ensure that the identified problems can be solved in a targeted manner. Create a self-learning iterative optimization model based on the quality diagnosis results of each chip. The model should be able to integrate chip quality assessment data, packaging parameters, and environmental monitoring data to achieve dynamic adjustment and optimization. Choose appropriate algorithms (such as random forests or support vector machines in machine learning) so that the model can learn from historical data and identify which parameters have the greatest impact on packaging quality. Use historical packaging quality data, environmental conditions, and packaging parameters as input to train the self-learning model. Ensure the diversity and completeness of the data set so that the model can fully understand the packaging effect under different conditions. Improve the accuracy and generalization ability of the model through cross-validation and hyperparameter tuning to ensure that it can effectively predict the packaging quality under different environments and parameters. In the actual packaging process, monitor the environmental parameters and packaging quality in real time, and dynamically adjust the packaging parameters (such as filling pressure, speed, and temperature) according to the prediction results of the self-learning model. After each packaging is completed, record the new data and feed it back to the model to achieve continuous learning and optimization. Ensure that the model can continuously update its prediction ability based on the latest data. Integrate the self-learning model with automated packaging equipment to ensure that the system can automatically adjust the packaging parameters based on real-time feedback. This will achieve a high degree of automation in the packaging process, improving efficiency and accuracy. During this process, the automated system is tested to ensure that it can quickly respond to environmental changes and quality feedback, reduce human intervention, and improve overall production efficiency. Apply the optimization model to the new packaging batch, monitor the packaging quality in real time, and compare it with the previous packaging results. Evaluate the performance of the model in actual application to ensure that it can effectively improve the packaging quality. Collect and analyze the quality data of the new batch to verify the accuracy and effectiveness of the model, and further optimize it if necessary. Build a feedback mechanism to regularly review the performance of the optimization model and record the quality data and environmental parameters of each package to further adjust and optimize the model.Ensure that the team holds regular review meetings to analyze the differences between the model's predicted results and actual results, and propose improvements to ensure the model's continuous evolution and adaptability.

[0022] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: obtaining a real-time monitoring image of the microfluidic chip to be packaged in the packaging box; Step S12: marking chip structure feature points of the real-time monitoring image of the microfluidic chip, and extracting a plurality of chip structure feature points; Step S13: positioning the packaging box based on multiple chip structural feature points, thereby obtaining the precise position coordinates of the chip; Step S14: performing visual recognition of preset positioning marks on the real-time monitoring image of the microfluidic chip to extract the position information of the preset positioning marks of the packaging box; Step S15: performing chip position alignment and calibration processing according to the precise chip position coordinates and the preset positioning mark position information of the packaging box, and collecting the calibrated chip monitoring image.

[0023] In this embodiment, the packaging box is equipped with a high-resolution camera and imaging system to ensure that the subtle features of the microfluidic chip can be captured. The imaging device should have good contrast and color reproduction capabilities to facilitate subsequent feature extraction and analysis. Ensure that the installation position of the imaging device is reasonable so that the chip status in the packaging box can be monitored in all directions. Start the real-time monitoring system and set appropriate parameters such as exposure time, focal length and gain to obtain a clear image. Adjust according to the ambient light conditions to ensure that high-quality images can be obtained under different lighting conditions. Collect images regularly to ensure that every step of the chip state change can be captured in time during the packaging process. This process can be programmed to achieve automatic image acquisition and reduce human intervention. Marking the feature points of the microfluidic chip is a key step in accurate positioning. These feature points usually include the corners, edges and other significant structural features of the chip, which can provide a reference for subsequent positioning and calibration. Accurately marking feature points helps to improve positioning accuracy and ensure the smooth progress of the packaging process. Image processing techniques, such as edge detection, corner detection and other algorithms, are used to automatically identify and mark the structural feature points of the chip. Commonly used algorithms include Harris corner detection, Shi-Tomasi corner detection, etc. It is necessary to ensure that the selection of feature points is consistent with the characteristics of the chip structure to provide accurate point information for subsequent positioning. In the acquired real-time monitoring image, the selected feature point detection algorithm is applied to automatically extract multiple chip structure feature points. The marking results are superimposed on the original image for visual inspection. The extracted feature point coordinate information is recorded to form a feature point list to provide data support for subsequent positioning and calibration. Positioning based on the extracted chip structure feature points is the key to achieving accurate chip packaging. By determining the specific position of the chip in the packaging box, the subsequent packaging operation can be effectively guided. Accurate positioning helps to reduce packaging errors and improve the performance and reliability of the chip. Geometric transformation algorithms, such as homography or affine transformation, are used to calculate the correspondence between feature points. These algorithms can deduce the relative position of the chip in the packaging box based on the known feature point coordinates. Determine the corresponding source feature points and target feature points, and ensure accurate matching of the feature points during calculation. Input the extracted feature point data and use the selected algorithm to calculate the precise position coordinates of the chip in the packaging box. This process may require multiple iterations to improve positioning accuracy. The final calculated coordinate information is recorded and compared with the preset packaging position to ensure the accuracy of chip positioning. The presence of preset positioning marks in the packaging box provides additional reference points for chip positioning. The accuracy of chip position calibration can be further enhanced by visually identifying positioning marks. This step ensures that the placement of the chip is consistent with the design mark of the packaging box, thereby avoiding packaging problems caused by position deviation. Computer vision techniques, such as template matching and shape recognition, are used to identify preset positioning marks in the packaging box.These algorithms can be implemented using open source libraries such as OpenCV. It is necessary to ensure that the pattern design of the preset mark is unique and easy to distinguish from the background to improve the accuracy and efficiency of recognition. Apply the selected visual recognition algorithm in the real-time monitoring image to automatically detect and extract the position information of the positioning mark. This process should include image preprocessing, such as filtering and threshold processing, to improve recognition accuracy. Record the recognized positioning mark position information for comparison and analysis with the precise position coordinates of the chip. The chip position alignment calibration process is the last step of the entire packaging process to ensure that the chip is accurately aligned with the preset positioning mark in the packaging box. Accurate calibration can improve the quality of packaging and ensure the performance and reliability of the chip. Through calibration, potential problems caused by position deviation can be eliminated to ensure the stability of the chip during use. Image registration technology is used to align the precise position coordinates of the chip and the position information of the positioning mark. Rigid transformation or non-rigid transformation methods can be used, depending on the type of deviation in the chip position. Ensure that the physical size of the chip and the design parameters of the packaging box are taken into account during the calibration process to achieve the best alignment effect. Compare the extracted chip position coordinates with the positioning mark position information to calculate the required transformation parameters. Apply the selected calibration method to adjust the chip position. Finally, collect the calibrated chip monitoring image to verify the calibration effect. Record the calibrated image and its related parameters to ensure the traceability of subsequent analysis.

[0024] In this embodiment, the specific steps of step S15 are: The chip position error is calculated in real time based on the preset positioning mark position information of the packaging box, so as to generate the packaging position error of the current chip; Performing in-depth chip shape analysis on the real-time monitoring image of the microfluidic chip to extract chip shape features; Calculating the chip geometry according to the real-time monitoring image of the microfluidic chip to generate chip geometry parameters; Perform position error compensation calculation on the packaging position error of the current chip according to the chip shape characteristics and chip geometric size parameters, so as to obtain the position error compensation value; The chip position calibration drive of the packaging box is performed based on the position error compensation value, and the calibrated chip monitoring image is collected.

[0025] In this embodiment, real-time chip position error calculation is an important step to ensure accurate positioning of the microfluidic chip in the packaging box. By calculating the deviation between the actual position of the chip and the preset positioning mark, the position error can be discovered and corrected in time to ensure the packaging quality. Accurate error calculation can provide necessary data for subsequent compensation and calibration to avoid functional failure or performance degradation caused by position deviation. Collect the precise position coordinates of the chip and the preset positioning mark position information of the packaging box. Ensure that the two data sets are in the same coordinate system for direct comparison and calculation. For each chip, record the coordinates of its center point and the coordinates of the feature points around it to obtain more detailed position information. Calculate the current packaging position error of the chip, usually using the Euclidean distance formula to calculate the distance between the actual position and the preset position, and the chip shape depth analysis is the basis for extracting the chip geometric features. By analyzing the shape features, the boundaries, corners, curves and other information of the chip can be obtained, providing data basis for subsequent geometric size calculations. This process helps to identify the difference between the actual shape of the chip and the designed shape to ensure the accuracy of the package. Image processing techniques such as edge detection and contour extraction are used to perform in-depth analysis of the chip shape. Common algorithms include Canny edge detection and Hough transform. Before in-depth analysis, the real-time monitoring image needs to be preprocessed to improve the clarity and contrast of the image and ensure the accuracy of feature extraction. Apply the selected edge detection algorithm to the preprocessed image to automatically extract the shape features of the chip. Record the extracted edge points, contour information, etc. to form a shape feature data set. Visualize the extracted features to ensure the accuracy of the extraction results and provide a basis for subsequent geometric dimension calculations. The calculation of chip geometric dimension parameters is a key step to ensure that the chip is properly placed in the packaging box. By calculating the actual size of the chip, it can be compared with the design size to identify potential packaging problems. Accurate geometric dimension data can provide a basis for subsequent error compensation to ensure the normal function of the chip. Through the extracted shape features, the geometric dimension parameters of the chip are calculated, including the length, width, height and angle of the chip. Geometric principles and image processing techniques can be used, such as calculating the minimum enclosing rectangle of the contour. Set appropriate calibration parameters to ensure that the calculation results are consistent with the actual physical size. According to the extracted edge features, the geometric dimension parameters of the chip are calculated. For example, use the minimum enclosing rectangle to determine the width and length of the chip, and record these parameters. Ensure that the results of the geometric dimension calculation are repeatable, and record the parameters and results of each calculation for subsequent analysis and comparison. Based on the error value, shape characteristics and geometric dimension parameters, use linear or nonlinear optimization algorithms for compensation calculations. The calculation formula is usually: compensation value = error + shape feature correction value. It is necessary to set a suitable compensation strategy based on the specific structure and packaging requirements of the chip. Combine the calculated error value with the shape characteristics to generate the final compensation value. Record this compensation value and ensure its application in subsequent calibration processing.Perform multiple tests to verify the effectiveness of the compensation values ​​and ensure that the final result can improve the accuracy of the package. Use an automated control system to adjust the position of the chip based on the calculated compensation values. Servo motors or stepper motors can be used for precise driving to ensure that the chip is placed in the preset position. Ensure that the calibration system has a good feedback mechanism to monitor the position changes in real time during the adjustment process. Adjust the position of the chip based on the compensation value to ensure that the chip is finally aligned to the preset position. Record each step of the adjustment process for subsequent analysis. After the adjustment is completed, collect the calibrated chip monitoring image to verify the calibration effect and record the final position and deviation for quality control and subsequent improvements.

[0026] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: Perform visual inspection of chip internal components on the calibrated chip monitoring image, and mark all chip internal component nodes; Step S22: performing microfluidic channel analysis according to all chip internal component nodes to extract microfluidic channel information; Step S23: performing channel layout recognition on the microfluidic channel information to generate microfluidic channel layout features; Step S24: performing channel morphological structure analysis on the microfluidic channel information to generate microfluidic channel morphological structure features; Step S25: performing multi-channel flow topology correlation fitting according to the microfluidic channel layout characteristics and microfluidic channel morphological structure characteristics to construct a chip packaging microfluidic channel topological structure model.

[0027] In this embodiment, a high-resolution optical microscope or industrial camera is used to obtain chip monitoring images to ensure that the clarity and details of the image are visible. A magnification of at least 1000 times is usually selected to accurately capture the characteristics of each component. Image processing software (such as ImageJ or OpenCV) is selected to process and analyze the acquired images and prepare for subsequent node marking. The calibrated chip is placed under a microscope and photographed from multiple angles to obtain comprehensive image data. Ensure that the image of each internal component can be clearly displayed. The acquired images are processed and algorithms such as edge detection and morphological processing are applied to identify the components inside the chip. On the processed image, the node position of each component is marked and its coordinate information is recorded. Ensure that the marking includes all key components such as pumps, valves, channels, etc. Generate a marked image and export the node coordinate data for use in subsequent steps. Based on the component nodes marked in the previous step, an analysis model of the microfluidic channel is constructed. Determine the starting and ending nodes of the channel and draw a connection diagram of the channel. Use CAD software or a custom analysis tool to enter the node coordinates and connection relationships to generate a geometric model of the channel. Analyze the constructed model and extract the geometric features of the channel, including the length, width, radius of curvature, etc. These features are crucial for subsequent layout recognition and morphological structure analysis. Record the characteristic parameters of each channel and generate a channel feature table. Use graphic analysis and pattern recognition technology to perform layout recognition on the extracted microfluidic channel information. Use algorithms (such as Dijkstra algorithm) to analyze the connection relationship of the channels. Combined with geometric features, set thresholds to judge the width and shape of the channel to ensure the accuracy of layout recognition. Analyze the extracted channel information, identify and mark the layout features of different channels, such as inlets, outlets, diversion points, and confluence points. Generate a layout diagram and record the layout relationship of each channel. Generate a report on the layout features of the microfluidic channel and record the main parameters of the layout. Use geometric analysis methods and fluid mechanics models to analyze the morphological characteristics of the microfluidic channel. Finite element analysis (FEA) or computational fluid dynamics (CFD) simulations can be used to evaluate the effect of channel shape on flow. Set analysis parameters such as flow rate, viscosity, pressure, etc. Perform a detailed morphological analysis on the extracted channel information, and calculate the geometric features of each channel, such as area, perimeter, and curvature. Ensure the accuracy of the data for subsequent structural feature generation. Record the analysis results, including the morphological parameters of each channel, and generate a structural feature table. Use topological analysis and fluid dynamics models, combined with the extracted channel layout features and morphological structure features, to perform multi-channel flow topology correlation fitting. Use network analysis methods to construct the topological structure of the flow. Determine fitting parameters such as flow velocity, flow distribution, pressure loss, etc. Draw a topological structure model based on the layout and morphological structure characteristics of the microfluidic channel, and mark the flow direction and connection relationship of each channel. Use graphical tools to generate a visual model.Document the parameters and assumptions used in model building and generate detailed topology model reports.

[0028] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: obtaining a packaging requirement log; performing a current packaging material characteristic analysis according to the packaging requirement log, and extracting packaging material characteristic information; Step S32: Calculating the filling pressure requirement of each channel of the chip packaging microchannel topological structure model according to the packaging material characteristic information, and extracting the filling pressure requirement of each channel; Step S33: performing adaptive filling flow rate estimation on the chip packaging microchannel topological structure model to obtain an adaptive filling rate of each channel; Step S34: Automated packaging and filling are performed according to the filling pressure requirement of each channel and the adaptive filling rate of each channel, and environmental monitoring parameters of the microfluidic packaging box are collected.

[0029] In this embodiment, the packaging requirement log is collected and sorted, including the specific requirements of the project, design specifications and material selection criteria. This information usually comes from the records of the project management system or the product development team. Ensure that the log contains the required packaging material type, thickness, temperature resistance, chemical stability and other key parameters for subsequent analysis. According to the obtained packaging requirement log, select the appropriate packaging material for characteristic analysis. Common packaging materials include epoxy resin, polymer, ceramic, etc., and the physical and chemical properties of each material need to be evaluated. Collect relevant literature and technical data to extract the characteristic information of the packaging material, such as density, viscosity, thermal conductivity and mechanical strength. These parameters are crucial to the performance in the packaging process. The extracted material characteristic information is organized into a table for subsequent analysis and reference. Ensure that the characteristic data of each material is accurate and complete, so as to facilitate comparison with the requirements in the packaging process. When recording material characteristic information, pay special attention to parameters related to fluidity and filling, which will directly affect the subsequent filling pressure and flow rate calculation. Based on the characteristic information of the packaging material, select a suitable fluid mechanics model to calculate the filling pressure requirement of each channel. Commonly used models include the Hagen-Poset flow equation and the Bernoulli equation, which can describe the flow behavior of fluids in channels. Consider the geometric characteristics of the channel, such as length, width, curvature, and inlet / outlet conditions, to ensure that the calculation model can accurately reflect the actual situation. The microfluidic topology model of the chip package is analyzed channel by channel, and the filling pressure requirements are calculated based on the material properties and channel geometry using a determined fluid mechanics model. The filling pressure requirements for each channel are recorded, including the calculation results and the parameters used. Ensure the accuracy and traceability of the data. The filling pressure requirements for each channel are organized into a table for subsequent analysis and reference. The pressure values ​​of each channel and their corresponding material properties are recorded for adjustment and optimization during the filling process. Adaptive filling flow rate inference is performed using a fluid dynamics simulation method. Computational fluid dynamics (CFD) software can be used to simulate the flow behavior of fluids in microfluidic channels under different filling conditions. The viscosity, flow characteristics, and geometric characteristics of the channel are considered in the simulation to ensure the accuracy of the inference results. Flow rate inference is performed for each channel, and the calculated filling pressure requirements and packaging material characteristics are input to simulate the flow of fluids in the channel. Record the adaptive fill rate for each channel and analyze how the flow rate changes under different conditions. Ensure that the simulation results can reflect the dynamic characteristics of the actual filling process. Configure the automated filling equipment to ensure that it has the ability to accurately control the filling pressure and flow rate. The equipment should be able to adjust according to the calculated filling pressure requirements and adaptive fill rate. Perform pre-inspection and calibration of the equipment to ensure measurement accuracy and control stability during the filling process. Start the automated package filling program based on the filling pressure requirements and adaptive fill rate for each channel. The equipment will perform the filling operation channel by channel according to the set parameters.During the filling process, the filling pressure and flow rate are monitored in real time to ensure that they meet the preset parameters and adjust the operating status of the equipment in a timely manner. During the filling process, the environmental monitoring parameters of the microfluidic packaging box are collected, including temperature, humidity, air pressure, etc. These parameters are crucial for evaluating the stability of the filling process and product quality. The monitoring data is recorded and compared with the parameters of the filling process for subsequent improvement and optimization.

[0030] In this embodiment, step S4 includes the following steps: Step S41: performing real-time temperature calculation on the environmental monitoring parameters of the microfluidic packaging box and extracting the real-time temperature value; Step S42: Analyze the time series changes of the real-time temperature value to generate a time series temperature change curve in the box; Step S43: performing multi-time point pressure fluctuation calculations according to the environmental monitoring parameters of the microfluidic packaging box to generate a pressure fluctuation trend graph; Step S44: performing optimal packaging environment parameter analysis according to the packaging requirement log to extract the optimal packaging environment parameters; Step S45: performing dynamic packaging parameter deviation calculation on the time-series temperature variation curve and the pressure fluctuation trend diagram in the box according to the optimal packaging environment parameters to obtain a dynamic packaging parameter deviation value; Step S46: adjusting the environmental parameters of the microfluidic packaging box in real time according to the dynamic packaging parameter deviation value, thereby constructing a real-time packaging box parameter adjustment strategy.

[0031] In this embodiment, a high-precision temperature sensor is installed in the microfluidic packaging box to ensure that the sensor can monitor the temperature changes in the box in real time. These sensors usually have digital output functions and can be directly connected to the data acquisition system. Configure the data acquisition system to read the value of the temperature sensor regularly, and set the reading interval to 1 second to capture the temperature changes in time. Start the data acquisition system and start recording the output data of the temperature sensor. Ensure that the system can run stably and accurately record the temperature value read each time. Perform real-time calculations on the collected temperature data to ensure that the current temperature value can be updated in time, and mark and process abnormal data to prevent it from affecting subsequent analysis. During the data acquisition process, check the working status of the temperature sensor regularly to ensure the accuracy and reliability of the data. Record the real-time temperature value and organize it into time series data to facilitate subsequent time series change analysis. After the real-time temperature value is extracted, it is stored in the database for use in subsequent steps and to ensure the integrity and traceability of the data. Extract the real-time temperature data from the database to ensure data integrity and remove any abnormal values. Use data cleaning techniques such as median filtering or moving average to smooth the data and reduce the impact of noise. Arrange the cleaned data in chronological order to ensure that the data can accurately reflect the time series of temperature changes. Use statistical analysis tools to analyze the time series changes of temperature data. Calculate the temperature change rate at each time point to identify the trend and pattern of temperature fluctuations. Generate a temperature change curve and use a line chart to show the temperature change over time, ensuring that the chart is clear and easy to read. Record the generated time series temperature change curve, including the temperature value and change trend at key time nodes. When analyzing the results, pay attention to identifying the cause of temperature fluctuations, such as changes in the external environment or heat release during the packaging process. Integrate the analysis results into a report to provide a reference for subsequent pressure fluctuation calculations and packaging environment parameter analysis. Install a pressure sensor in the microfluidic packaging box to ensure that it can monitor the pressure changes in the box in real time. Select a sensor with high sensitivity and fast response capabilities to accurately capture pressure fluctuations. Configure the data acquisition system and set the same reading frequency as the temperature sensor to ensure synchronous monitoring of temperature and pressure. Start the data acquisition system and start recording the output data of the pressure sensor. Monitor pressure changes in real time and verify the data to ensure its accuracy. Calculate the pressure fluctuation at each time point, analyze the amplitude and frequency of pressure changes, and identify possible abnormal fluctuations. Organize the pressure data into a time series, generate a pressure fluctuation trend chart, and use a line chart to show the change of pressure over time. Make sure the chart is clear to facilitate the observation of the law of pressure fluctuations. Record the generated pressure fluctuation trend chart and analyze the key changes in the chart to provide a basis for subsequent packaging environment parameter analysis. Combined with the packaging demand log, identify key parameters related to the environment, such as temperature range, pressure range, humidity requirements, etc. These parameters are critical to ensuring packaging quality.According to the project requirements and material characteristics, formulate the recommended standards for the optimal environmental parameters to ensure that these standards can meet the needs of the packaging process. Combined with the real-time monitored temperature and pressure data, analyze the difference between the current environmental conditions and the optimal conditions. Use statistical methods to calculate the deviation of the current environmental parameters to determine the direction and magnitude of the adjustment required. Through comparative analysis, extract the optimal packaging environmental parameters, such as target temperature, target pressure and humidity level, to ensure that these parameters can remain stable during the packaging process. Organize the extracted optimal packaging environmental parameters into a report, record the specific value and recommended range of each parameter, so as to facilitate subsequent adjustment and monitoring. Ensure the traceability of all data and provide a basis for the calculation of dynamic packaging parameter deviation. Construct a dynamic parameter deviation calculation model based on the filling pressure requirement and adaptive filling rate of each channel. Ensure that the model can reflect the relationship between the real-time monitoring data and the optimal environmental parameters. Determine the calculation formula to calculate the deviation value between the current environmental parameters and the optimal parameters at each time point. Calculate the dynamic packaging parameter deviation value channel by channel based on the real-time monitoring data and the extracted optimal environmental parameters. Record the deviation value of each channel to ensure the accuracy and reliability of the data. Analyze the trend of the deviation and identify the channels that need to be adjusted in order to facilitate the subsequent immediate environmental parameter adjustment. The calculated dynamic packaging parameter deviation values ​​are organized into a report, recording the deviation of each channel and its possible influencing factors. The deviation results are analyzed to identify potential improvement opportunities and provide a basis for the subsequent adjustment of packaging environment parameters. According to the calculated dynamic packaging parameter deviation values, an immediate environmental parameter adjustment strategy is formulated. Ensure that the strategy can effectively deal with the current deviation and quickly restore to the optimal packaging environment. Determine the priority of the adjustment and focus on the channels with large deviations to improve the overall packaging effect. Start the automated control system and implement real-time adjustments to temperature, pressure and humidity according to the immediate adjustment strategy. Ensure that the adjustment process can quickly respond to changes in monitoring data. Monitor the adjusted environmental parameters to ensure that they gradually approach the optimal values, and record the data changes during the adjustment process. After the adjustment is implemented, continue to monitor the changes in environmental parameters and evaluate the effect of the adjustment strategy. Analyze the gap between the adjusted parameters and the optimal parameters and make necessary strategy optimization. Record the feedback information during the adjustment process to provide guidance for the subsequent packaging process and ensure that the packaging environment is always in the best state.

[0032] In this embodiment, step S5 includes the following steps: Step S51: Acquire a chip monitoring image after microfluidic packaging is completed; Step S52: performing global image brightness enhancement processing on the completed chip monitoring image to obtain a global brightness optimized image; Step S53: performing packaging defect detection on the global brightness optimized image to identify packaging defect data; Step S54: performing a quantitative analysis of the sealing performance of the microchannel according to the identified packaging defect data to obtain the sealing performance information of the microchannel; Step S55: performing packaging material distribution uniformity analysis on the global brightness optimization image, and extracting a quantitative value of packaging material distribution uniformity; Step S56: Perform a comprehensive packaging quality assessment based on the microchannel sealing information and the packaging material distribution uniformity quantified value to obtain a packaging quality assessment report.

[0033] In this embodiment, after the microfluidic encapsulation is completed, a high-resolution microscope or industrial camera is used for image acquisition. Ensure that the optical system of the device is calibrated so that a clear image can be obtained. Set a suitable light source to ensure that the brightness and contrast of the image are moderate during the acquisition process to avoid overexposure or underexposure. White light LED or halogen lamp is usually used for illumination. Place the packaged chip under a microscope and adjust the focus and viewing angle to ensure that the surface and internal features of the chip can be fully captured. Take pictures from multiple angles to ensure that the image can cover all areas of the chip, especially key areas such as microchannels and package edges. Set the shooting interval to collect enough image data at different angles and positions. Store the collected image data in a database, and ensure that the file name and related information (such as shooting time, angle, etc.) of each image are marked to facilitate subsequent processing and analysis. Check the quality of the image to ensure that all images are clear and usable, and remove blurred or out-of-focus images to ensure the accuracy of subsequent analysis. Use image processing software (such as ImageJ, Photoshop or OpenCV) to import the collected monitoring images. These software provide a wealth of image processing tools that can adjust brightness and contrast. Ensure that the software can handle high-resolution images and has batch processing capabilities so that multiple images can be processed uniformly. In the image processing software, use the histogram equalization method to enhance the global brightness of the image. This method adjusts the pixel distribution of the image to improve the overall brightness and contrast, making the details clearer. For specific images, use gamma correction or brightness / contrast adjustment tools to further optimize the image effect. Record the parameter settings for each image processing to ensure repeatability. After the brightness enhancement is completed, save the processed image and compare it with the original image to ensure that the enhancement effect is as expected. The generated optimized image should clearly show the details of the microchannel and package area. Store the optimized image in a database for subsequent defect detection and analysis. Use image processing algorithms for package defect detection. Common methods include edge detection, morphological processing, and pattern recognition. Selecting an appropriate method can effectively identify defects in the image. If possible, use machine learning algorithms (such as convolutional neural networks) for defect identification. Use labeled defect images when training the model to improve the accuracy of detection. Input the global brightness optimized image into the defect detection system and run the selected detection algorithm. Based on the set threshold, the algorithm will automatically detect and mark defect areas in the image, such as bubbles, cracks or uneven coatings. Record the type, location and size of each detected defect and generate a defect data report for subsequent analysis. Analyze the test results to assess the severity and possible impact of the defects. Organize the defect data into a table to record the number, type and distribution of defects. The organized defect data will provide a basis for subsequent microchannel sealing analysis and ensure the accuracy of subsequent analysis. Select an appropriate quantitative analysis method to evaluate the sealing of the microchannel.Common methods include airtightness testing and fluid dynamics simulation to determine whether there is leakage in the microchannel. Combined with the detected packaging defect data, analyze the impact of defects on sealing, focusing on the types of defects that may cause leakage. Based on the defect data, determine the sealing score of each microchannel, and use the set scoring criteria to evaluate the integrity of the package. For example, bubbles and cracks may cause sealing failure. Run a fluid dynamics simulation to simulate the flow of fluid in the microchannel and evaluate the risk of fluid leakage. Determine the sealing index by calculating the flow rate and pressure of the fluid. Organize the analysis results into a report to record the sealing information of each channel, including the sealing score, leakage risk assessment, and possible influencing factors. Ensure the accuracy of the results to provide a reliable basis for subsequent packaging quality assessment. Use image statistical analysis methods to evaluate the distribution uniformity of packaging materials. Methods such as standard deviation calculation, variance analysis, or uniformity index (such as Gini coefficient) can be used. Select a suitable analysis tool to ensure that it can process the global brightness optimized image and output quantitative uniformity indicators. Segment the global brightness optimized image to extract the packaging material area. Calculate the distribution of brightness values ​​in this area and analyze its uniformity. Record each parameter setting during the calculation process to ensure that the results are repeatable. Calculate the uniformity quantification value and analyze its results. Organize the extracted packaging material distribution uniformity quantification value into a report, record the uniformity index and its meaning, so as to provide support for the subsequent packaging quality evaluation. Combine the results of defect detection and sealing analysis to comprehensively evaluate the quality of the package. Construct a comprehensive packaging quality evaluation model based on the microchannel sealing information and the packaging material distribution uniformity quantification value. Determine the weight of each indicator to facilitate the accuracy of the comprehensive evaluation results. Set the evaluation criteria, including different grades such as excellent, good, medium, and poor, to facilitate the quantification of the evaluation results. Input each evaluation index into the comprehensive evaluation model to calculate the packaging quality score. Determine the quality grade of the package according to the set criteria. Record the evaluation results and analyze the main factors affecting the packaging quality for subsequent improvements. Organize the comprehensive evaluation results and generate a packaging quality evaluation report. The report should include the specific values ​​of each indicator, the evaluation conclusions and improvement suggestions.

[0034] In this embodiment, step S6 includes the following steps: Step S61: diagnose the packaging quality of each chip one by one according to the packaging quality assessment report, and extract chips with unqualified packaging quality; Step S62: Tracing the packaging link of the packaging quality assessment report to identify the packaging defect link; Step S63: optimizing packaging parameters for packaging defect links according to the microchannel sealing information and the quantified value of packaging material distribution uniformity to obtain packaging optimization parameters; Step S64: Based on the packaging optimization parameters, adaptive secondary packaging processing is performed on the chips with unqualified packaging quality, and self-learning iterative optimization is performed based on the real-time packaging box parameter adjustment strategy to build an automated packaging test optimization model.

[0035] In this embodiment, the latest packaging quality assessment report is extracted to ensure that the report contains the packaging quality scores and defect information of all chips. This information usually includes the sealing score, material uniformity quantification value and defect type of each chip. The packaging quality of each chip is analyzed one by one, and the set quality standard (such as packaging quality score threshold) is used to determine whether it meets the requirements. The qualified standard is usually set to score more than 80 points, and chips below this value are considered unqualified. During the analysis process, the specific quality indicators and defect types of each unqualified chip are recorded for subsequent improvement and optimization. The information of the unqualified chip is sorted into a list, including its identification, defect type, packaging quality score and related parameters. Ensure that the list information is clear and accurate for subsequent analysis and processing. Classify the extracted unqualified chips, analyze the common defect types and frequency of occurrence, and provide a basis for subsequent defect identification and optimization. Collect all data related to the packaging process, including environmental monitoring parameters, operation records, material batches and production equipment information. These data are usually stored in the production management system. Ensure the integrity and accuracy of the data for effective traceability analysis. For each unqualified chip, track each link in the packaging process to identify the links that may cause defects. Tools such as fault tree analysis (FTA) or fishbone diagrams can be used to analyze the root causes of defects. Record the key parameters of each link, such as temperature, pressure, time, material batch, etc., to facilitate the identification of potential influencing factors. Comprehensively analyze the collected data to identify the links related to packaging defects. This may include material preparation, environmental control, equipment calibration, and operating processes. Record the identified defective links in the report as a basis for subsequent optimization. Comprehensively analyze the sealing information of the microchannel and the quantitative value of the uniformity of the packaging material distribution to identify the key parameters related to the packaging defect link. These parameters usually include filling pressure, filling rate, and material selection. Set optimization goals, such as improving the sealing score to more than 90 points, and ensure that the uniformity of material distribution meets the set standards. Based on the analysis results, adjust the key parameters in the packaging process to improve the packaging quality. For example, increase the filling pressure, adjust the filling rate, or change the material batch. Record the specific parameter settings of each optimization to ensure traceability for subsequent implementation.

[0036] Organize the optimized parameters into a report, recording the basis for adjusting each parameter and the expected effect. This report will provide guidance for the subsequent secondary packaging process. Perform secondary packaging on unqualified chips according to the optimized parameters. Ensure that the packaging equipment can be adjusted according to the new parameter settings to ensure that the filling pressure and flow rate meet the optimization requirements. During the secondary packaging process, monitor the environmental parameters in real time to ensure that they meet the immediate packaging box parameter adjustment strategy. Start the automated packaging equipment to perform secondary packaging on unqualified chips. The equipment should be able to adaptively adjust key variables in the filling process, such as pressure and flow rate, according to the set optimization parameters. Monitor the real-time data during the secondary packaging process to ensure that all parameters are within the set range, and record the relevant data for subsequent analysis. Build a self-learning iterative optimization model based on real-time monitoring data and packaging processing results. Analyze the relationship between historical data and new data through machine learning algorithms to identify the best packaging parameter combination. Record the learning process and optimization results of the model to facilitate continuous adjustment and optimization of the subsequent packaging process to ensure the continuous improvement of chip packaging quality.

[0037] In this embodiment, an automated packaging and testing system for a microfluidic chip is provided, which is used to perform the automated packaging and testing method for the microfluidic chip as described above, including: A position calibration module is used to obtain a real-time monitoring image of a microfluidic chip to be packaged in a packaging box; perform chip position alignment and calibration processing on the real-time monitoring image of the microfluidic chip, and collect the calibrated chip monitoring image; A microfluidic channel topology module is used to perform visual inspection of chip internal components and multi-channel flow topology correlation fitting on the calibrated chip monitoring image to construct a chip packaging microfluidic channel topology structure model; The packaging and filling execution module is used to obtain the packaging demand log, and automatically execute the packaging and filling of the chip packaging microfluidic topology model, and collect the environmental monitoring parameters of the microfluidic packaging box; An immediate adjustment module is used to perform dynamic packaging parameter deviation calculation on the environmental monitoring parameters of the microfluidic packaging box and perform immediate environmental parameter adjustment, thereby constructing an immediate packaging box parameter adjustment strategy; The quality assessment module is used to obtain chip monitoring images after microfluidic packaging is completed, and to conduct a comprehensive packaging quality assessment to obtain a packaging quality assessment report; The iterative optimization module is used to diagnose the packaging quality of each chip according to the packaging quality assessment report, and to perform self-learning iterative optimization according to the real-time packaging box parameter adjustment strategy to build an automated packaging test optimization model.

[0038] The present invention uses a high-resolution camera to perform real-time image acquisition on the microfluidic chip, and can accurately obtain the current position, size and shape of the chip. This can provide the most accurate basic data for subsequent packaging operations. The automatic alignment and calibration of the chip not only eliminates the deviation in manual operation, but also greatly improves the accuracy of the packaging process. Accurate alignment can avoid the position offset of the chip during the packaging process, ensure the consistency of the chip packaging position and shape, and reduce the possibility of packaging failure. Through the calibrated image, accurate image data is further provided for the internal structure analysis and packaging test of the chip, and important prerequisite data is provided for subsequent steps (such as flow topology analysis and packaging process). Computer vision technology is used to automatically identify and mark all key components inside the chip (such as microfluidic channels, holes, valves, etc.). This not only improves the accuracy of detection, but also avoids omissions and errors in manual detection. By fitting the multi-channel flow topology in the microfluidic chip, a topological structure model of the microchannel can be constructed. This model can accurately describe the fluid transmission path in the chip, which helps to optimize fluid control, flow regulation and material distribution in the packaging process. Through the accurate flow topology model, the flow pattern of the fluid in the chip after packaging can be effectively predicted, providing a theoretical basis for the subsequent packaging filling process, ensuring that the fluid is not blocked or bubbled during the filling process. The packaging parameters are automatically obtained according to the packaging demand log, avoiding the inconsistency in manual intervention, and adjusting the filling flow rate, pressure, temperature and other parameters according to actual needs. Through precise automatic filling control, the microfluidic channel can accurately fill the required materials to ensure that the fluid filling of each channel is uniform, avoiding errors and inconsistencies in manual operation. Real-time collection of environmental parameters (such as temperature, humidity, pressure, etc.) in the packaging box provides real-time data support for subsequent packaging quality analysis and optimization. This step ensures that the environmental factors in the packaging process are always in the optimal state. Through real-time analysis of the environmental monitoring data of the packaging box, the deviation of environmental factors such as temperature and pressure can be quickly identified and adjusted in time. This greatly reduces the instability caused by fluctuations in environmental factors during the packaging process. Dynamic deviation calculation and instant adjustment strategy ensure that the environmental parameters are always kept within the optimal range, avoiding inappropriate temperature or pressure fluctuations affecting the packaging quality. The stability of the packaging process is guaranteed, especially in long-term packaging operations. Adjusting the packaging environment in real time can ensure that all chips are under the same environmental conditions during the packaging process, enhancing the consistency and reliability of the packaging process and reducing the packaging defect rate. The chip monitoring image after packaging can provide detailed chip packaging status. Comprehensive evaluation can comprehensively analyze the integrity, sealing and material distribution of chip packaging to ensure high quality packaging. Through automatic image analysis, small defects generated during the packaging process, such as bubbles, cracks, and uneven materials, can be identified. If these defects are not discovered in time, they may lead to subsequent poor functions or failures, so it is very important to discover and repair them in time.The packaging quality assessment report provides data support for the improvement of the packaging process, which is helpful for subsequent packaging optimization and quality control. The packaging quality of each chip can be diagnosed individually to ensure that each chip meets the packaging standards. Unqualified chips are marked and the problems are located to avoid putting unqualified chips into the next stage. Based on real-time feedback data, the system can self-learn and optimize various parameters in the packaging process (such as temperature, pressure, filling rate, etc.) to continuously improve the packaging quality. Through data accumulation and analysis, the automated packaging test optimization model is gradually improved. The model can adjust process parameters based on historical packaging data, thereby optimizing future packaging processes and improving overall packaging efficiency and quality.

[0039] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0040] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may 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 the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An automated packaging and testing method for a microfluidic chip, characterized in that: The following steps are involved: Step S1: obtaining a real-time monitoring image of the microfluidic chip to be packaged in the packaging box; Performing chip position alignment and calibration processing on the real-time monitoring image of the microfluidic chip, and collecting the calibrated chip monitoring image; Step S2: performing visual inspection of chip internal components and multi-channel flow topology correlation fitting on the calibrated chip monitoring image to construct a chip packaging microchannel topology structure model; Step S3: Obtaining the packaging demand log, and automatically performing packaging filling on the chip packaging microfluidic channel topology model, and collecting environmental monitoring parameters of the microfluidic packaging box; Step S4: performing dynamic packaging parameter deviation calculation on the environmental monitoring parameters of the microfluidic packaging box, and performing real-time environmental parameter adjustment, thereby constructing a real-time packaging box parameter adjustment strategy; Step S5: obtaining a chip monitoring image after microfluidic packaging is completed, and performing a comprehensive packaging quality assessment to obtain a packaging quality assessment report; Step S6: Perform chip packaging quality diagnosis for each chip according to the packaging quality assessment report, perform self-learning iterative optimization according to the real-time packaging box parameter adjustment strategy, and build an automated packaging test optimization model.

2. The automated packaging and testing method for a microfluidic chip according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: obtaining a real-time monitoring image of the microfluidic chip to be packaged in the packaging box; Step S12: marking chip structure feature points of the real-time monitoring image of the microfluidic chip, and extracting a plurality of chip structure feature points; Step S13: positioning the packaging box based on multiple chip structural feature points, thereby obtaining the precise position coordinates of the chip; Step S14: performing visual recognition of preset positioning marks on the real-time monitoring image of the microfluidic chip to extract the position information of the preset positioning marks of the packaging box; Step S15: performing chip position alignment and calibration processing according to the precise chip position coordinates and the preset positioning mark position information of the packaging box, and collecting the calibrated chip monitoring image.

3. The automated packaging and testing method for a microfluidic chip according to claim 2, characterized in that: The specific steps of step S15 are: The chip position error is calculated in real time based on the preset positioning mark position information of the packaging box, so as to generate the packaging position error of the current chip; Performing in-depth chip shape analysis on the real-time monitoring image of the microfluidic chip to extract chip shape features; Calculating the chip geometry according to the real-time monitoring image of the microfluidic chip to generate chip geometry parameters; Perform position error compensation calculation on the packaging position error of the current chip according to the chip shape characteristics and chip geometric size parameters, so as to obtain the position error compensation value; The chip position calibration drive of the packaging box is performed based on the position error compensation value, and the calibrated chip monitoring image is collected.

4. The automated packaging and testing method for a microfluidic chip according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: Perform visual inspection of chip internal components on the calibrated chip monitoring image, and mark all chip internal component nodes; Step S22: performing microfluidic channel analysis according to all chip internal component nodes to extract microfluidic channel information; Step S23: performing channel layout recognition on the microfluidic channel information to generate microfluidic channel layout features; Step S24: performing channel morphological structure analysis on the microfluidic channel information to generate microfluidic channel morphological structure features; Step S25: performing multi-channel flow topology correlation fitting according to the microfluidic channel layout characteristics and microfluidic channel morphological structure characteristics to construct a chip packaging microfluidic channel topological structure model.

5. The automated packaging and testing method for a microfluidic chip according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: obtaining a packaging requirement log; performing a current packaging material characteristic analysis according to the packaging requirement log, and extracting packaging material characteristic information; Step S32: Calculating the filling pressure requirement of each channel of the chip packaging microchannel topological structure model according to the packaging material characteristic information, and extracting the filling pressure requirement of each channel; Step S33: performing adaptive filling flow rate estimation on the chip packaging microchannel topological structure model to obtain an adaptive filling rate of each channel; Step S34: Automated packaging and filling are performed according to the filling pressure requirement of each channel and the adaptive filling rate of each channel, and environmental monitoring parameters of the microfluidic packaging box are collected.

6. The automated packaging and testing method for a microfluidic chip according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: performing real-time temperature calculation on the environmental monitoring parameters of the microfluidic packaging box and extracting the real-time temperature value; Step S42: Analyze the time series changes of the real-time temperature value to generate a time series temperature change curve in the box; Step S43: performing multi-time point pressure fluctuation calculations according to the environmental monitoring parameters of the microfluidic packaging box to generate a pressure fluctuation trend graph; Step S44: performing optimal packaging environment parameter analysis according to the packaging requirement log to extract the optimal packaging environment parameters; Step S45: performing dynamic packaging parameter deviation calculation on the time-series temperature variation curve and the pressure fluctuation trend diagram in the box according to the optimal packaging environment parameters to obtain a dynamic packaging parameter deviation value; Step S46: adjusting the environmental parameters of the microfluidic packaging box in real time according to the dynamic packaging parameter deviation value, thereby constructing a real-time packaging box parameter adjustment strategy.

7. The automated packaging and testing method for a microfluidic chip according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: Acquire a chip monitoring image after microfluidic packaging is completed; Step S52: performing global image brightness enhancement processing on the completed chip monitoring image to obtain a global brightness optimized image; Step S53: performing packaging defect detection on the global brightness optimized image to identify packaging defect data; Step S54: performing a quantitative analysis of the sealing performance of the microchannel according to the identified packaging defect data to obtain the sealing performance information of the microchannel; Step S55: performing packaging material distribution uniformity analysis on the global brightness optimization image, and extracting a quantitative value of packaging material distribution uniformity; Step S56: Perform a comprehensive packaging quality assessment based on the microchannel sealing information and the packaging material distribution uniformity quantified value to obtain a packaging quality assessment report.

8. The automated packaging and testing method for a microfluidic chip according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: diagnose the packaging quality of each chip one by one according to the packaging quality assessment report, and extract chips with unqualified packaging quality; Step S62: Tracing the packaging link of the packaging quality assessment report to identify the packaging defect link; Step S63: optimizing packaging parameters for packaging defect links according to the microchannel sealing information and the quantified value of packaging material distribution uniformity to obtain packaging optimization parameters; Step S64: Based on the packaging optimization parameters, adaptive secondary packaging processing is performed on the chips with unqualified packaging quality, and self-learning iterative optimization is performed based on the real-time packaging box parameter adjustment strategy to build an automated packaging test optimization model.

9. An automated packaging and testing system for a microfluidic chip, characterized in that: The method for performing the automated packaging and testing of the microfluidic chip according to claim 1 comprises: A position calibration module is used to obtain a real-time monitoring image of a microfluidic chip to be packaged in a packaging box; perform chip position alignment and calibration processing on the real-time monitoring image of the microfluidic chip, and collect the calibrated chip monitoring image; A microfluidic channel topology module is used to perform visual inspection of chip internal components and multi-channel flow topology correlation fitting on the calibrated chip monitoring image to construct a chip packaging microfluidic channel topology structure model; The packaging and filling execution module is used to obtain the packaging demand log, and automatically execute the packaging and filling of the chip packaging microfluidic topology model, and collect the environmental monitoring parameters of the microfluidic packaging box; An immediate adjustment module is used to perform dynamic packaging parameter deviation calculation on the environmental monitoring parameters of the microfluidic packaging box and perform immediate environmental parameter adjustment, thereby constructing an immediate packaging box parameter adjustment strategy; The quality assessment module is used to obtain chip monitoring images after microfluidic packaging is completed, and to conduct a comprehensive packaging quality assessment to obtain a packaging quality assessment report; The iterative optimization module is used to diagnose the packaging quality of each chip according to the packaging quality assessment report, and to perform self-learning iterative optimization according to the real-time packaging box parameter adjustment strategy to build an automated packaging test optimization model.

Images