MOSFET collinear packaging control method and system

Abstract

The invention discloses an MOSFET collinear packaging control method and system, and relates to the technical field of semiconductor manufacturing, and the method comprises the steps: obtaining a chip distribution frame line graph of a to-be-cut wafer, carrying out the optimization of a cutting shortest path according to the graph, and generating a wafer cutting recommended path; and obtaining time sequence information of cutting speed and depth. Cutting temperature time sequence information is generated through a cutting temperature prediction model in combination with cutting path, speed and depth information; cooling control is optimized according to the temperature time sequence information, and recommended cooling liquid flow and pressure time sequence information are obtained; and wafer cutting is carried out based on the cutting and cooling parameters, and a plurality of separated chips are obtained for MOSFET collinear integrated packaging. The technical problems of inaccurate temperature control and low cooling efficiency in the wafer cutting process in the prior art are solved, and the technical effect of improving the accuracy of temperature control and the cooling efficiency in the wafer cutting process is achieved.

Description

Technical Field

[0001] The present application relates to the field of semiconductor manufacturing technology, and in particular to a MOSFET co-linear packaging control method and system. Background Art

[0002] In the production process of modern semiconductor devices, wafer cutting is a crucial process link, especially in the manufacture of MOSFET co-linear packaging, where cutting accuracy directly affects chip performance and packaging quality. The temperature control method in the prior art usually relies on real-time monitoring and adjustment, which has the problem of long time delay, resulting in inaccurate temperature control and low cooling efficiency. This not only affects the stability of the cutting process, but also increases the loss and manufacturing cost of the equipment. During the cutting process, the heat generated by changes in cutting speed and depth may cause local overheating and affect the cutting accuracy, especially in applications requiring high-precision packaging. How to accurately control the temperature and optimize the cooling process to improve cutting accuracy and stability has become a difficult problem in current technology.

[0003] In the current related technologies, there are technical problems such as inaccurate temperature control and low cooling efficiency during wafer cutting. Summary of the invention

[0004] The present application solves the technical problems of inaccurate temperature control and low cooling efficiency in the wafer cutting process in the prior art by providing a MOSFET co-linear packaging control method and system.

[0005] The present application provides a MOSFET co-linear packaging control method, comprising: Obtain a chip distribution frame diagram of a wafer to be cut; optimize the shortest cutting path according to the chip distribution frame diagram to obtain a recommended wafer cutting path; obtain cutting speed timing information and cutting depth timing information; process the recommended wafer cutting path, the cutting speed timing information and the cutting depth timing information through a cutting temperature prediction model to obtain cutting temperature timing information; optimize cooling control according to the cutting temperature timing information to obtain recommended coolant flow timing information and recommended coolant pressure timing information; perform wafer cutting according to the cutting speed timing information, the cutting depth timing information, the recommended coolant flow timing information and the recommended coolant pressure timing information to obtain a number of separate chips for MOSFET co-linear integration packaging.

[0006] The present application provides a MOSFET co-line packaging control system, comprising: A chip distribution frame line diagram acquisition module, the chip distribution frame line diagram acquisition module is used to obtain the chip distribution frame line diagram of the wafer to be cut; a cutting shortest path optimization module, the cutting shortest path optimization module is used to optimize the cutting shortest path according to the chip distribution frame line diagram, and obtain a wafer cutting recommended path; a timing information acquisition module, the timing information acquisition module is used to obtain cutting speed timing information and cutting depth timing information; a cutting temperature timing information acquisition module, the cutting temperature timing information acquisition module is used to optimize the wafer cutting recommended path, the cutting speed, and the cutting depth through a cutting temperature prediction model. The invention relates to a wafer cutting module, wherein the wafer cutting module is used to process the cutting speed timing information and the cutting depth timing information to obtain the cutting temperature timing information; a cooling control optimization module, wherein the cooling control optimization module is used to optimize the cooling control according to the cutting temperature timing information to obtain the coolant recommended flow timing information and the coolant recommended pressure timing information; and a wafer cutting module, wherein the wafer cutting module is used to perform wafer cutting according to the cutting speed timing information, the cutting depth timing information, the coolant recommended flow timing information and the coolant recommended pressure timing information to obtain a plurality of separate chips for MOSFET co-linear integration packaging.

[0007] The MOSFET co-linear packaging control method and system proposed in this application first obtains the chip distribution frame diagram of the wafer to be cut, and optimizes the shortest cutting path based on the diagram to generate the recommended wafer cutting path; obtains the timing information of the cutting speed and depth. Through the cutting temperature prediction model, combined with the cutting path, speed and depth information, the cutting temperature timing information is generated; the cooling control is optimized according to the temperature timing information to obtain the recommended coolant flow and pressure timing information; wafer cutting is performed based on the cutting and cooling parameters, and multiple separated chips are obtained for MOSFET co-linear integrated packaging, achieving the technical effect of improving the accuracy of temperature control and cooling efficiency during wafer cutting. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0009] Figure 1 A schematic flow chart of a MOSFET co-linear packaging control method provided in an embodiment of the present application; Figure 2 A schematic structural diagram of a MOSFET co-linear packaging control system provided in an embodiment of the present application.

[0010] Explanation of reference numerals: chip distribution frame diagram acquisition module 10 , cutting shortest path optimization module 20 , timing information acquisition module 30 , cutting temperature timing information acquisition module 40 , cooling control optimization module 50 , wafer cutting module 60 . DETAILED DESCRIPTION

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0012] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0013] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0014] The present application embodiment provides a MOSFET co-linear packaging control method, such as Figure 1 As shown, the method includes: Step S100, obtain the chip distribution frame diagram of the wafer to be cut. Specifically, select an optical imaging device with high resolution and resolution of micron level or higher, such as an industrial microscope or a wafer detection optical scanning system, debug and calibrate the lens focal length, light source brightness angle, set the appropriate magnification, and prepare the data acquisition storage module. Then place the wafer, place it in the center of the imaging device stage and perpendicular to the optical axis, use the positioning mark to record the initial position, and choose to image from different angles and multiple perspectives, control the imaging device to scan point by point in a preset manner, and transmit and save the image data in real time. Then pre-process the collected original image, use algorithms such as median filtering and Gaussian filtering to reduce noise, and use histogram equalization or contrast stretching technology to enhance the contrast. Then apply edge detection algorithms such as the Canny operator, and accurately extract chip edge information through steps such as Gaussian filtering, gradient calculation, non-maximum suppression and dual threshold detection, and then use mathematical morphology closed operations to connect the edges, and use the least squares method to fit the curve to construct a chip distribution frame diagram represented by a polygon or rectangular frame, clearly showing the chip position, shape and layout, and providing basic data for subsequent cutting processes.

[0015] Step S200, according to the chip distribution frame diagram, the shortest cutting path is optimized to obtain the recommended path for wafer cutting. Specifically, the chip distribution frame diagram is digitized, the key feature information of the chip is extracted and sorted, and the appropriate path optimization algorithm model is selected according to the wafer cutting requirements and constraints, such as Dijkstra, A* algorithm or genetic, simulated annealing algorithm, etc. Then, the graph structure is constructed with the chip boundaries and connection points as graph nodes and the cutting path as edges, and weights are assigned to the edges according to factors such as cutting distance, difficulty, chip importance and thermal effect. Select the starting and target nodes. For the graph theory algorithm, the adjacent nodes are expanded from the starting node and the path cost and the predecessor node information are updated until the target node is taken out; the heuristic algorithm randomly generates the initial cutting path solution as the population, evaluates it according to the fitness function, and iterates and optimizes it through genetic operations or annealing strategies. Afterwards, the preliminary shortest path is optimized and verified to check whether it meets the constraints such as the physical limitations of the cutting equipment, process requirements, and conflict avoidance. Adjustments and corrections are made through local search, backtracking, etc., and actual uncertainty factors are analyzed for redundant design and fault-tolerant analysis. The final recommended wafer cutting path can shorten the cutting stroke, ensure chip quality, provide a basis for MOSFET co-linear packaging, and improve production efficiency and economic benefits.

[0016] Step S300, obtain the cutting speed timing information and cutting depth timing information. Specifically, the cutting equipment and sensors are selected and installed. For the cutting speed, a high-precision laser Doppler speed meter or encoder is selected, installed on the moving parts of the cutting tool and calibrated; for the cutting depth, a high-precision LVDT or capacitive displacement sensor is used, installed on the tool holder and other components and calibrated. Then, a data acquisition system is built, including a data acquisition card, a signal conditioning circuit and a computer software. The speed and depth data acquisition are synchronized through a unified clock or timestamp, and the sensor signals are collected at a high sampling frequency and converted and stored. Then, the sensor is preheated and initialized before the cutting equipment is started. During cutting, data is continuously collected and recorded in real time. At the same time, the data is preliminarily analyzed. If there is an abnormal fluctuation, the equipment and sensor are checked to ensure that the cutting is normal and the data is accurate. Finally, the collected data is post-processed, and a filtering algorithm is used to remove noise, check integrity and interpolate to repair missing data, compare the preset process parameters to verify accuracy, find out the cause of deviation and correct it, and provide a reliable data basis for subsequent process optimization.

[0017] Step S400, through the cutting temperature prediction model, the wafer cutting recommended path, the cutting speed timing information and the cutting depth timing information are processed to obtain the cutting temperature timing information. Specifically, a large amount of historical wafer cutting data covering different wafer materials, cutting equipment parameters, paths and corresponding speeds, depth settings and actual cutting temperature monitoring values ​​are collected, pre-processed, checked for integrity and accuracy, abnormal data are removed, and interpolation and supplementation of missing values ​​are normalized. Then, according to the characteristics of wafer cutting, a suitable prediction model architecture is selected, such as a heat conduction model based on physical principles, an empirical formula model or a machine learning model (taking a neural network as an example), and a multi-layer perceptron structure including an input layer (receiving characteristic parameters of the wafer cutting recommended path, cutting speed and depth timing information), a hidden layer (determining the number of layers and nodes through experiments, and selecting a nonlinear activation function) and an output layer (outputting the predicted temperature value) is constructed. The pre-processed data is divided into a training set, a validation set and a test set to train the model, and a suitable loss function and optimization algorithm are used to iterate the training until convergence to obtain a cutting temperature prediction model. Finally, the model is verified with an independent test set, and the predicted temperature timing information is compared with the actual measured value. The error index is calculated to evaluate the accuracy. If it is not ideal, it is optimized by adjusting the model structure parameters, training algorithm parameters, or increasing the diversity of training data to enable accurate prediction, provide a reliable basis for cooling control and cutting process optimization, and ensure chip quality and manufacturing process stability.

[0018] In a possible implementation, the wafer cutting recommended path, the cutting speed timing information and the cutting depth timing information are processed by a cutting temperature prediction model to obtain cutting temperature timing information, and step S400 further includes step S410 to obtain wafer cutting equipment parameters, wherein the wafer cutting equipment parameters include cutting path structure parameters, cutting groove structure parameters, connecting rib structure parameters, and cutting machine precision parameters. Specifically, in order to obtain the wafer cutting equipment parameters, high-precision measuring instruments are required to perform measurement and evaluation operations. For the cutting path structural parameters, the width is accurately measured to the micron level using an electron microscope or laser profilometer, because the width affects the heat dissipation and material removal rate. At the same time, the measurement depth is related to the tool cutting depth and affects the energy and temperature distribution. The surface roughness must also be recorded. The parameters are of great significance to building the model; the cutting groove structural parameters are measured by precision equipment to determine its shape, size and groove wall inclination angle. Different shapes and sizes will have a significant impact on the cutting stress distribution and coolant flow characteristics, providing detailed information for temperature prediction; for the connecting rib structural parameters, its thickness, height, and width are measured. The thickness affects the cutting resistance and heat, and the proportional relationship is related to the stress and heat conduction path. The material composition and thermal conductivity must also be clarified to help understand the law of heat propagation; when evaluating the precision parameters of the cutting machine, the tool positioning error in the X, Y, and Z directions is measured using standard calibration blocks and three-dimensional coordinate measuring machines to determine its impact on the accuracy of the cutting path and heat generation, and the motion repeatability is measured to determine the cutting stability and temperature fluctuations. The feed speed control accuracy is analyzed to ensure cutting according to the preset speed sequence to avoid excessive heat generation. The precision parameters allow us to fully analyze the impact of uncertain factors in cutting on temperature.

[0019] Step S420, the cutting temperature prediction model is constructed with the cutting path structural parameters, the cutting groove structural parameters, the connecting rib structural parameters, and the cutting machine precision parameters as constraints. Specifically, the model selection and architecture design are carried out based on the physical characteristics of the wafer cutting process and the characteristics of the acquired equipment parameters, and a finite element analysis model (FEM) or a neural network model can be selected. The finite element analysis model discretizes the cutting process into small units based on the principles of heat conduction, convection and radiation to solve the heat balance equation to predict the temperature distribution, but the calculation is complex and requires in-depth analysis of the physical process and precise setting of parameters; the neural network model has strong nonlinear fitting capabilities and is suitable for processing complex multivariate problems. Taking it as an example, a multilayer perceptron architecture with input, hidden, and output layers is designed. The input layer nodes are determined according to parameters such as cutting paths, grooves, connecting ribs, and cutting machine precision. The hidden layer first tries 2 to 3 layers, with dozens to hundreds of nodes in each layer, and uses activation functions such as ReLU and tanh to enhance the expressiveness. The output layer outputs the predicted temperature value. When constructing the model, the cutting paths, grooves, connecting rib structural parameters, and cutting machine precision parameters are incorporated as constraints. In the finite element model, parameters are used to define geometric shapes, material properties and boundary conditions, such as setting the heat conduction boundary according to the width and depth of the cutting path, determining the coolant flow channel and heat transfer coefficient according to the cutting groove, setting the conduction coefficient according to the thermal conductivity of the connecting ribs, and considering the impact of the uncertainty of the cutting path on the temperature according to the accuracy of the cutting machine; the neural network model adds these parameters as part of the feature vector in the training data to automatically capture the relationship, and uses L1 or L2 regularization to prevent overfitting, ensuring that the model accurately predicts the temperature based on the constraints, and improves generalization and prediction accuracy. The model is trained using a large amount of experimental or simulated data, with the actual measured temperature as the target value, and the model parameters are continuously adjusted, such as the material property parameters of the finite element, the weights and biases of the neural network, to minimize the error between the predicted value and the actual value. After multiple iterations to the preset convergence conditions, such as the mean square error is less than the threshold or reaches the predetermined number of training rounds, the obtained model can reflect the impact of equipment parameters on temperature and provide a reliable tool for temperature prediction.

[0020] Step S430, through the cutting temperature prediction model, the wafer cutting recommended path, the cutting speed timing information and the cutting depth timing information are processed to obtain the cutting temperature timing information. Specifically, before using the cutting temperature prediction model, the relevant data needs to be prepared and preprocessed. For the wafer cutting recommended path, it is converted into geometric characteristic parameters such as path length, number of turning points, and path curvature, so as to more intuitively show the complexity of the cutting path and the potential impact on the temperature; the cutting speed and cutting depth timing information are normalized to map their numerical range to the [0,1] interval to ensure that they are comparable to other parameter magnitudes, and the data integrity and continuity are checked at the same time. If there are missing data or abnormal values, interpolation or correction methods are used in time to ensure that the data quality of the input model is reliable. After the preprocessing is completed, the characteristic parameters of the wafer cutting recommended path, the cutting speed and depth timing information, and the previously acquired wafer cutting equipment parameters (including cutting paths, cutting grooves, connecting rib structure parameters and cutting machine precision parameters) are used as input and transmitted to the constructed cutting temperature prediction model. The model performs a series of calculations on the input data based on the internal mathematical model and the parameters obtained through training. The finite element analysis model obtains the temperature distribution of each time step during the cutting process by solving the heat conduction equation, and the neural network model uses the forward propagation algorithm to calculate the predicted temperature value of each time step, thereby generating the cutting temperature timing information. During the prediction process, pay close attention to the model output results to check whether there are unreasonable situations such as excessively high or low temperatures, sudden temperature changes, etc. Once an abnormality is found, immediately check the accuracy of the input data and the running status of the model to eliminate possible problems, ensure that the obtained cutting temperature timing information is accurate, and truly reflect the temperature change trend during wafer cutting, provide strong support for subsequent cooling control optimization and wafer cutting process optimization, promote the smooth development of subsequent processes such as MOSFET co-linear packaging, improve the quality and efficiency of the semiconductor manufacturing process, and reduce product defect rates and production costs caused by temperature problems.

[0021] In a possible implementation, the cutting temperature prediction model is constructed with the cutting path structure parameters, the cutting groove structure parameters, the connecting rib structure parameters, and the cutting machine precision parameters as constraints, and step S420 further includes step S421, configuring the cutting path structure similarity threshold, the cutting groove structure similarity threshold, the connecting rib structure similarity threshold, and the cutting machine precision deviation distance threshold. Specifically, various thresholds are determined based on an in-depth analysis of the wafer cutting process and previous empirical data. For the cutting path structure similarity threshold, in view of the important influence of its width, depth, and surface roughness on the cutting temperature, after analyzing the temperature variation law under different combinations and the temperature control precision requirements of actual production, such as when the cutting path width deviation is ±5 microns, the depth deviation is ±10 microns, and the surface roughness deviation is ±0.5 microns, the temperature impact is acceptable, and the deviation range is converted into a comprehensive threshold for sample screening. The threshold of similarity of the cutting groove structure is set according to the influence mechanism of its shape, size (groove width, groove depth, groove length and spacing) and groove wall inclination angle on temperature. By simulating the flow of coolant and heat transfer, the threshold with less influence on temperature is determined when the groove width and groove depth deviation is within ±15% and the groove wall inclination angle deviation is within ±5 degrees (same shape), so as to ensure the similarity of the sample cutting groove structure and the reliability of the temperature prediction basis. When determining the threshold of similarity of the connecting rib structure, the close relationship between its thickness, height, width and material thermal conductivity and the cutting stress distribution and heat conduction path is considered. After mechanical and thermal analysis and sensitivity testing, the similarity judgment standard is set to within ±8% of the thickness deviation, within ±10% of the height and width deviation, and within ±15% of the material thermal conductivity deviation, so as to ensure the comparability and regularity of the influence of the sample connecting rib structure on temperature. In setting the cutting machine accuracy deviation distance threshold, for key indicators such as the cutting tool positioning accuracy, motion repeatability and feed speed control accuracy, according to the equipment technical specifications and actual cutting accuracy requirements, such as the positioning accuracy is set to ±0.02 mm based on the equipment nominal ±0.01 mm combined with the actual fluctuation, the motion repeatability is set to a certain multiple (such as 2 times) of the tool position deviation standard deviation of multiple repeated cutting experiments as the threshold, and the feed speed control accuracy is set to a speed deviation percentage of ±5% as the threshold based on the speed stability requirements and the impact of speed fluctuations on temperature. This ensures that the samples included in the model have similar cutting machine accuracy conditions, thereby improving the accuracy and reliability of the model's prediction of cutting temperature.

[0022] Step S422, obtaining a first cutting sample, wherein the first cutting sample has a cutting path structure label, a cutting groove structure label, a connecting rib structure label, and a cutting machine precision label. Specifically, a sample collection system covering a variety of situations is established to record in detail the wafer cutting process under different models and process parameter settings. During each cutting experiment, the width, depth, and surface roughness of the cutting path are accurately measured and organized into cutting path structure labels; the shape, size, and inclination angle of the cutting groove are accurately recorded to generate a cutting groove structure label; the thickness, height, width, and thermal conductivity of the connecting rib are measured to form a connecting rib structure label; high-precision instruments such as a three-coordinate measuring machine and a laser interferometer are used to measure the positioning accuracy, motion repeatability, and feed speed control accuracy of the cutting tool, and converted into a cutting machine precision label, thereby collecting the first cutting sample with a complete label to provide data resources for subsequent work. During the collection process, it is necessary to ensure the diversity and representativeness of the samples, and include different wafer materials (such as common silicon wafers and specially doped and composite structure wafers), different cutting process parameters (setting the cutting speed range from low speed to high speed and the cutting depth range from shallow cutting to deep cutting and conducting multiple experiments) and different cutting equipment (selecting equipment from different manufacturers, with different precision levels and technical characteristics), so that the first cutting sample can reflect various actual production situations and enhance the generalization ability and prediction accuracy of the model.

[0023] Step S423, compare the cutting path structure label, the cutting groove structure label, the connecting rib structure label, and the cutting machine precision label with the cutting path structure parameters, the cutting groove structure parameters, the connecting rib structure parameters, and the cutting machine precision parameters to obtain the cutting path structure similarity, cutting groove structure similarity, connecting rib structure similarity, and cutting machine precision deviation distance. Specifically, perform sample comparison calculation, so that based on the preset similarity calculation method, each structure label and precision label of the first cutting sample and the cutting path, groove, connecting rib structure parameters and cutting machine precision parameters of the model to be constructed are accurately compared and calculated for similarity. To calculate the cutting path structure similarity, a weighted distance algorithm based on comprehensive width, depth, and surface roughness is used, such as assigning weights of 0.4, 0.4, and 0.2 to these three items respectively, calculating the difference between the sample and the target parameter in each dimension and weighted summing them, and obtaining an index with a value between 0 and 1. The closer to 1, the higher the similarity. Calculate the structural similarity of the cutting groove. For its shape, size and groove wall inclination angle, first convert the shape into numerical code, then combine the size and other parameters into a feature vector, and calculate it with the target vector using the cosine similarity algorithm. The above calculation method has good accuracy and stability for complex factors. Calculate the structural similarity of the connecting ribs. According to its parameter characteristics, the relative deviation method is used to calculate the deviation of each parameter of the sample relative to the target and weighted average (such as 0.3, 0.2, 0.2, 0.3) to obtain the index, which reflects the degree of closeness to the target structural parameters to judge the similarity of temperature influence. Calculate the precision deviation distance of the cutting machine, directly measure the difference between the sample and the target precision parameters, and sum the weighted sum according to the preset weights (positioning accuracy 0.5, motion repeatability 0.3, feed speed control accuracy 0.2) to obtain the index, which intuitively reflects the degree of deviation, provides a quantitative basis for sample screening, ensures the consistency of the sample and target cutting conditions in accuracy, and reduces the model prediction error caused by accuracy differences.

[0024] Step S424, when the cutting path structural similarity is greater than or equal to the cutting path structural similarity threshold, and the cutting groove structural similarity is greater than or equal to the cutting groove structural similarity threshold, the connecting rib structural similarity is greater than or equal to the connecting rib structural similarity threshold, and the cutting machine precision deviation distance is less than or equal to the cutting machine precision deviation distance threshold, the first cutting sample is added to the cutting temperature prediction model to construct a sample set. Specifically, an automated sample screening process is established, and after completing the calculation of the cutting path, cutting groove, connecting rib structural similarity and the cutting machine precision deviation distance, the results are compared with the preset thresholds one by one. If the similarity of the cutting path structure of a first cutting sample meets the standard, it means that the key parameters of its cutting path structure for temperature are similar to the target cutting conditions, and it can provide temperature prediction information for the model; if the similarity of the cutting groove structure meets the requirements, the cutting groove structure characteristics of the sample are similar to the target, and the effects of the coolant flow and heat transfer characteristics on temperature are comparable; if the similarity of the connecting rib structure meets the standard, it means that its influence on temperature is similar to the target, which is helpful for model learning; the precision deviation distance of the cutting machine is within the threshold, which ensures that the precision of the sample and the target cutting process is consistent, and reduces the interference of precision differences on model prediction. Only when the sample meets these conditions at the same time can it be included in the cutting temperature prediction model to build a sample set as the basic data for subsequent model training. Through strict screening, it is ensured that the samples are highly similar and representative, accurately reflect the temperature change law under the target cutting conditions, and improve the model training and prediction effect. When adding samples, each sample should be recorded and numbered in detail, covering the original cutting experimental conditions, various parameters, and similarity and deviation distance calculation results, so as to facilitate traceability analysis in model training optimization, understand the learning response of the model to the sample characteristics, and help improve the model.

[0025] Step S425, when the sample set for constructing the cutting temperature prediction model is greater than or equal to the preset number of samples, the cutting temperature prediction model is trained. Specifically, a reasonable preset number of samples is set, which requires a comprehensive analysis of factors such as model complexity, data diversity, and requirements for prediction accuracy. More complex models (such as neural network models with more hidden layers and nodes) require more samples to avoid overfitting; if the samples cover a variety of wafer materials, cutting process parameters, and equipment types, relatively few samples may also meet basic training requirements. For example, for a medium-complexity neural network cutting temperature prediction model, if the samples cover more than 3 wafer materials, more than 5 process parameter combinations, and more than 2 equipment types, the preset sample size can be set to about 500; if the model complexity is low or the data diversity is small, it can be appropriately reduced, but generally not less than 200, to ensure that the model learns enough temperature change laws and feature relationships to have prediction capabilities. When the number of samples in the sample set for constructing the cutting temperature prediction model reaches the standard, the training program is started. According to the selected model type (finite element analysis model, neural network model, etc.), select the appropriate training algorithm and parameter settings. The finite element model needs to determine the physical parameters such as thermal conductivity, boundary conditions, solution algorithm and number of iterations; the neural network model needs to select activation functions (such as ReLU, tanh, etc.), optimization algorithms (such as stochastic gradient descent, Adam optimizer, etc.) and learning rates, regularization parameters, etc., and then divide the sample set into training set, validation set and test set according to the ratio of 80%, 10%, and 10% to start training. During the training, the model parameters are continuously adjusted to gradually reduce the error between the prediction results of the training set and the actual temperature value. The validation set is used to monitor the performance to prevent overfitting. After multiple iterations, the validation set performance indicators (such as mean square error, mean absolute error, etc.) reach a stable and satisfactory level. After the model training is completed, the temperature under the target cutting conditions can be accurately predicted, which can be applied to the actual wafer cutting temperature prediction and control, helping to improve the quality and efficiency of semiconductor manufacturing.

[0026] Step S500, optimize the cooling control according to the cutting temperature timing information, and obtain the recommended coolant flow timing information and the recommended coolant pressure timing information. Specifically, it is necessary to collect data related to the cutting process, including cutting paths, grooves, connection rib structure parameters, cutting machine precision parameters and accurate cutting temperature timing information, and use high-precision temperature and ambient temperature monitoring equipment to ensure data accuracy, so as to lay the foundation for cooling control optimization. Then, a cooling sample collection experiment is carried out with various parameters and temperature information as constraints, and wafers are cut under different coolant flow and pressure combinations, and temperature, flow and pressure data are recorded to form a sample set. When the number of samples exceeds the threshold, a two-dimensional virtual coordinate system is constructed with the normalized data of coolant flow and pressure, and the samples are mapped. Then, LOF outlier analysis is performed on the samples in the coordinate system, outliers are excluded, and concentrated cooling samples less than or equal to the outlier factor threshold are extracted, and mean analysis is performed on them to obtain the recommended coolant flow timing information and the recommended coolant pressure timing information, so as to provide accurate parameters for the cooling control system, ensure cutting quality and subsequent processes, and improve semiconductor manufacturing performance and reliability.

[0027] In a possible implementation, the cooling control is optimized according to the cutting temperature timing information, and the recommended coolant flow timing information and the recommended coolant pressure timing information are obtained. Step S500 further includes step S510, and the ambient temperature monitoring value is obtained. Specifically, a plurality of high-precision temperature sensors are arranged near the wafer cutting work area. The sensors should have the ability to respond quickly and accurately measure, and can monitor the changes in ambient temperature in real time. The location selection of the sensor is very important, and it is necessary to avoid being directly affected by factors such as the heating of the cutting equipment itself and the heat dissipation of the coolant, so as to ensure that the collected temperature data can truly reflect the ambient temperature conditions of the cutting area. The data acquisition system is used to record and summarize the measured values ​​of the sensor regularly (for example, every few seconds) to form a continuous sequence of ambient temperature monitoring values, which provides basic data support for subsequent cooling control analysis. The sensor is calibrated and maintained to ensure that its measurement accuracy remains stable throughout the wafer cutting process, and to avoid inaccurate ambient temperature monitoring data due to sensor failure or error, thereby affecting the accuracy of cooling sample collection and coolant parameter optimization.

[0028] Step S520, obtaining wafer cutting equipment parameters, wherein the wafer cutting equipment parameters include cutting path structure parameters, cutting groove structure parameters, connecting rib structure parameters, and cutting machine precision parameters. Specifically, in order to obtain comprehensive and accurate wafer cutting equipment parameters, a variety of high-precision measurement tools and technologies need to be used. For the cutting path structure parameters, an optical measuring instrument or an electron microscope is used to measure the cutting path width at multiple positions and take the average to achieve micron-level accuracy, and the cutting path depth is determined by combining a depth measurement probe and image analysis technology. The surface roughness is recorded using a surface roughness measuring instrument. These parameters will affect the flow resistance, heat dissipation area, energy consumption and temperature distribution of the coolant, and are all recorded in detail as a subsequent basis. For the cutting groove structure parameters, three-dimensional laser scanning technology or precision mechanical measurement tools are used to accurately measure its shape (such as rectangular, V-shaped, U-shaped, etc.), size (groove width, groove depth, length and spacing, etc., strictly control measurement errors) and groove wall inclination angle (obtained by an angle measuring instrument or image algorithm). Because cutting grooves of different shapes and sizes have a significant impact on the flow and heat transfer of the coolant, the measured parameters will be sorted for subsequent work. For the structural parameters of the connecting ribs, the thickness is measured with a caliper and a micrometer, and the height and width are measured with a three-dimensional coordinate measuring instrument to clarify the impact of their proportional relationship on the stress distribution and heat conduction path of the wafer. A thermal conductivity measuring instrument or reference manual is used to determine the material composition and thermal conductivity. The measured parameters are accurately recorded and incorporated into the system. In terms of the evaluation of the precision parameters of the cutting machine, the positioning accuracy of the cutting tool is measured multiple times in the X, Y, and Z directions using a standard calibration block and a three-dimensional coordinate measuring instrument and the standard deviation is calculated. The position deviation is measured by repeatedly cutting the same path to statistically measure the motion repeatability. The feed speed control accuracy is evaluated using the speed sensor and control system feedback data. These precision parameters are recorded and analyzed in detail as important constraints for cooling sample collection and coolant parameter optimization to ensure that the coolant flow and pressure are adapted to the actual accuracy of the cutting machine and achieve effective cooling control.

[0029] Step S530, collect cooling samples with the cutting path structural parameters, the cutting groove structural parameters, the connecting rib structural parameters, the cutting machine precision parameters, and the cutting temperature timing information as constraints to obtain a cooling sample set, wherein any cooling sample has coolant flow recording timing data and coolant pressure recording timing data. Specifically, build a cooling sample collection experimental platform, which can accurately control the flow and pressure of the coolant, and monitor the temperature changes and other related parameters during the cutting process in real time. According to the predetermined cutting path, cutting groove, connecting rib structural parameters and cutting machine precision parameters, set the initial state of the cutting equipment to ensure that the cutting conditions are consistent for each experiment. Wafer cutting experiments are carried out under different coolant flow and pressure combinations. The range of flow and pressure should be reasonably determined based on actual production experience and theoretical analysis. For example, the coolant flow can be gradually increased from a lower starting value to a higher upper limit value, and the pressure also changes accordingly within a certain range to form multiple different flow-pressure combination working conditions. Under each working condition, the data acquisition system is used to record the changes of coolant flow and pressure over time during the cutting process, forming coolant flow recording time series data and coolant pressure recording time series data, while recording cutting temperature time series information and other related process parameters (such as cutting force, chip morphology, etc., these parameters can be used as auxiliary information for subsequent in-depth analysis of cooling effect). The data such as coolant flow, pressure and cutting temperature obtained from each experiment are sorted into a cooling sample. After many experiments under different working conditions, a large number of cooling samples are accumulated to form a cooling sample set. These samples reflect the changes in specific cutting equipment parameters and cutting temperature under different cooling conditions, providing a rich data basis for the subsequent optimization of coolant parameters. By analyzing and mining these samples, the most suitable coolant flow and pressure combination can be found to achieve effective control of cutting temperature and improve the quality and efficiency of wafer cutting.

[0030] Step S540, when the number of samples in the cooling sample set is greater than the cooling sample number threshold, the cooling sample set is distributed in a two-dimensional virtual coordinate system according to the coolant flow recording time series data and the coolant pressure recording time series data. Specifically, a cooling sample number threshold is determined, and the setting of the threshold requires comprehensive analysis of factors such as the complexity of the model, the diversity of the data, and the accuracy requirements for optimizing the coolant parameters. For more complex cooling models (such as high-precision models that consider the interaction of multiple factors), more samples are required to fully capture the complex relationship between coolant flow, pressure and cutting temperature; for relatively simple models, the number of samples can be appropriately reduced, but it is also necessary to ensure that it can cover a sufficient range of cooling conditions to ensure the reliability of the optimization results. Usually, the model performance under different sample numbers can be evaluated by combining experiments and simulation analysis to determine a suitable cooling sample number threshold. When the number of samples in the cooling sample set reaches or exceeds this threshold, the samples are processed to construct a two-dimensional virtual coordinate system. Using the normalized value of the coolant flow record time series data as the horizontal coordinate, the flow data of each cooling sample is normalized so that its value range is between [0,1], so as to make a unified comparison and analysis in the coordinate system; using the normalized value of the coolant pressure record time series data as the vertical coordinate, the pressure data is also normalized to construct a two-dimensional virtual coordinate system. Each sample in the cooling sample set is mapped to the two-dimensional virtual coordinate system according to its corresponding normalized flow and pressure values, so that each sample has a corresponding position in the coordinate system. In this way, the originally complex cooling sample data is intuitively displayed on a two-dimensional plane, which is convenient for subsequent center point sorting and coolant parameter optimization operations, and can more clearly observe the distribution law and trend of the samples, and find the potential optimal combination area of ​​coolant flow and pressure.

[0031] Step S550, center point sorting is performed according to the two-dimensional virtual coordinate system to obtain the coolant recommended flow timing information and the coolant recommended pressure timing information. Specifically, in the constructed two-dimensional virtual coordinate system, the cooling sample points are subjected to center point sorting operations to determine the coolant recommended flow timing information and the coolant recommended pressure timing information. A cluster analysis algorithm (such as a K-Means clustering algorithm) is used to cluster the cooling sample points in the coordinate system, and sample points with similar flow and pressure characteristics are clustered into one category. Through multiple iterative calculations, several main cluster centers are determined. Density analysis is performed on the sample points around each cluster center to calculate its local density, for example, using a distance-based density calculation method to determine the sample density of each cluster center. Based on the sample density of the cluster center and its relative distance to other cluster centers, the comprehensive score of each cluster center is calculated. A cluster center with a higher comprehensive score indicates that the sample points around it are more concentrated and representative, and are more likely to contain the optimal coolant flow and pressure combination. The cluster center with the highest comprehensive score is selected as the final center point. The normalized values ​​of the coolant flow and pressure corresponding to the center point are denormalized to obtain the actual recommended coolant flow timing information and recommended coolant pressure timing information. The recommended information reflects the changes in the optimal coolant flow and pressure that can effectively control the temperature during the cutting process under the constraints of given cutting equipment parameters and cutting temperature timing information. It provides precise control parameters for the actual wafer cutting cooling control system, and can dynamically adjust the coolant flow and pressure according to the real-time situation of the cutting process to ensure that the cutting temperature is maintained within the appropriate range, improve the quality and stability of wafer cutting, reduce chip defects and material damage caused by temperature problems, provide a high-quality wafer foundation for subsequent semiconductor manufacturing processes, and improve the production efficiency and economic benefits of the entire semiconductor manufacturing process.

[0032] In a possible implementation, when the number of samples in the cooling sample set is greater than the cooling sample number threshold, the cooling sample set is distributed in a two-dimensional virtual coordinate system according to the coolant flow record time series data and the coolant pressure record time series data, and step S540 further includes step S541, constructing a first coordinate axis with the normalized data of the coolant flow. Specifically, in the data preparation stage, the coolant flow record time series data in each cooling sample obtained from the cooling sample collection experiment is first collected, which reflects the actual changes in the coolant flow under different cutting conditions and time nodes. After that, the flow data is normalized using a linear normalization method, such as when the minimum and maximum values ​​of the original flow data are known, the flow value at a certain moment is converted into a normalized value in the interval [0,1], so that all flow data have a unified magnitude and value range, which is convenient for subsequent intuitive comparison and analysis. In the coordinate axis construction step, a two-dimensional coordinate environment supported by computer graphics or data analysis software is selected as the drawing plane, and the normalized coolant flow data value is used as the horizontal coordinate. The first coordinate axis is drawn in the horizontal direction, and the scale interval (such as 0.1 or 0.05, etc.) is reasonably determined according to the data accuracy and distribution. This is used to clearly locate the corresponding point position of the cooling sample, complete the construction of the first coordinate axis, and lay the foundation for the subsequent two-dimensional virtual coordinate system configuration to show the changes in coolant flow in different samples and its correlation with other factors.

[0033] Step S542, construct the second coordinate axis with the normalized data of the coolant pressure. Specifically, in the data preparation link, it is necessary to extract the coolant pressure record time series data contained in each sample from the existing cooling sample set, and the data can reflect the change of the coolant pressure in the corresponding cutting process. Then the coolant pressure data is normalized, similar to the normalization of the coolant flow data. According to the known minimum and maximum values ​​of the original pressure data, the normalized result of a certain pressure value is determined by the corresponding formula, so that all coolant pressure data are converted to the [0,1] interval range. In the process of generating the coordinate axis, in the same coordinate space selected previously, the vertical direction is used as the reference, and the value corresponding to the normalized coolant pressure data is set as the value of the ordinate to draw the coordinate axis, which is the second coordinate axis. Like the first coordinate axis, the scale interval is reasonably divided according to the data characteristics and analysis accuracy requirements (for example, every 0.1 is a scale unit), so that the value of each cooling sample in the coolant pressure dimension can accurately find the corresponding position on the coordinate axis. After the second coordinate axis is constructed, it is perpendicular to the first coordinate axis, and together they provide the necessary dimensional support for configuring the two-dimensional virtual coordinate system, which is conducive to the subsequent comprehensive analysis of the relationship between factors such as coolant flow, pressure and cutting temperature from a two-dimensional perspective.

[0034] Step S543, configure the two-dimensional virtual coordinate system according to the first coordinate axis and the second coordinate axis. Specifically, after respectively constructing the first coordinate axis representing the normalized data of the coolant flow rate and the second coordinate axis representing the normalized data of the coolant pressure, integrate the coordinate system, integrate the two into the same coordinate plane, make them perpendicular to each other and intersect at the coordinate origin (0,0), and the origin represents the normalized minimum state of the coolant flow rate and pressure, so that a two-dimensional virtual coordinate system is configured. In the coordinate system, any point in the plane can be represented by an ordered number pair, and the elements in the number pair correspond to the normalized data of the coolant flow rate and pressure respectively. Each cooling sample can find a unique coordinate position according to its corresponding normalized value, thereby presenting the complex cooling sample data in an intuitive two-dimensional plane form, providing a clear framework and basis for analysis operations such as center point sorting, and facilitating the exploration of the optimal combination of flow rate and pressure to control the cutting temperature. In order to make the two-dimensional virtual coordinate system clearer and easier to use, it is necessary to carry out labeling and improvement work. The corresponding variable names should be marked on the coordinate axes, such as the first coordinate axis should be marked as "Coolant flow (normalized)", and the second coordinate axis should be marked as "Coolant pressure (normalized)", and the original data units should be noted. At the same time, a title such as "Cooling sample coolant flow-pressure two-dimensional distribution coordinate system" should be added to clarify the purpose and the data relationship displayed. In addition, auxiliary explanatory information or legends should be added as needed to facilitate subsequent sample distribution observation, data analysis, and comparison and communication with other results, etc., to ensure that it can effectively serve the cooling control optimization goal and help obtain the recommended coolant flow timing information and recommended coolant pressure timing information.

[0035] In one possible implementation, center point sorting is performed according to the two-dimensional virtual coordinate system to obtain the recommended coolant flow timing information and the recommended coolant pressure timing information, and step S550 further includes step S551, obtaining the cooling sample distribution coordinate set of the cooling sample set. Specifically, based on the previously constructed two-dimensional virtual coordinate system, its horizontal coordinate is the normalized data of the coolant flow rate, and the vertical coordinate is the normalized data of the coolant pressure. In the coordinate system, each cooling sample corresponds to a specific coordinate point, which is determined by the normalized values ​​of its coolant flow rate and pressure. From the cooling sample set, the coordinate values ​​of each sample in the two-dimensional virtual coordinate system are extracted one by one, and the coordinate values ​​are organized into a data set, namely, the cooling sample distribution coordinate set. Each element in the set is a two-dimensional vector in the form of ,in represents the normalized value of coolant flow rate, Represents the normalized value of the cooling fluid pressure. In the above way, the distribution of cooling samples in two-dimensional space is presented in the form of a coordinate set, providing a data basis for subsequent outlier analysis, so as to further explore the distribution law and characteristics of cooling samples, find out possible abnormal samples, and optimize the selection of coolant parameters, realize precise control of cutting temperature, improve the quality and efficiency of wafer cutting, reduce chip defects and material waste caused by temperature runaway, and ensure the stability and reliability of the semiconductor manufacturing process.

[0036] Step S552: Perform LOF outlier analysis on the cooling sample distribution coordinate set to obtain a cooling sample outlier factor set. Specifically, the LOF (Local_Outlier_Factor) algorithm is used to perform outlier analysis on the cooling sample distribution coordinate set. The algorithm determines whether a sample point is an outlier based on the local density around the sample point. For each sample point in the coordinate set, , calculate the distance to other sample points, usually using the Euclidean distance formula ,in and are the coordinates of the two sample points. Then, based on the distance information, the local reachability density (LRD) of each sample point is determined.

[0037] LRD reflects the local density around the sample point. The calculation method is relatively complex and involves concepts such as the k-distance neighborhood of the sample point. In simple terms, it is to calculate the reachable density within a certain neighborhood of the sample point, taking into account the distribution of other sample points. Finally, the LOF value of each sample point, that is, the outlier factor, is calculated based on the LRD value. The larger the outlier factor, the greater the distribution difference between the sample point and other sample points in the local area, and the more likely it is an outlier. By performing such calculations on the entire cooling sample distribution coordinate set, a cooling sample outlier factor set is obtained, in which each element corresponds to the outlier factor of the corresponding sample in the original cooling sample set. These outlier factors will serve as an important basis for judging whether the sample is abnormal, helping us to screen out samples that do not conform to the overall distribution law, making subsequent analysis and coolant parameter recommendations more accurate and reliable, avoiding interference from abnormal samples, improving the accuracy and stability of cooling control optimization, and providing a more scientific and reasonable coolant flow and pressure recommendation scheme for temperature control during wafer cutting.

[0038] Step S553, extracting the centralized cooling samples less than or equal to the outlier factor threshold value from the cooling sample outlier factor set. Specifically, after obtaining the cooling sample outlier factor set, it is necessary to determine a suitable outlier factor threshold value. The threshold value can be determined by a variety of methods, such as statistical methods, observing the distribution of outlier factors, combining practical experience and understanding of data, and selecting a value that can reasonably distinguish normal samples from abnormal samples. It is also possible to analyze the sample screening results under different thresholds through experiments and simulations, evaluate their impact on the coolant parameter recommendation, and thus determine an optimal threshold value. Once the outlier factor threshold value is determined, the cooling samples corresponding to the elements less than or equal to the threshold value are screened out from the cooling sample outlier factor set, and these samples constitute the centralized cooling sample set. The distribution of these samples in the two-dimensional virtual coordinate system is relatively concentrated, representing the typical situation under normal cooling conditions, and their coolant flow and pressure combination has a high reference value, which can reflect the coolant parameter range that can effectively control the cutting temperature in most cases. By extracting these centralized cooling samples, outlier samples that may be caused by measurement errors, special working conditions or other abnormal factors are excluded, so that the subsequent mean analysis can more accurately reflect the optimal parameter trend under normal cooling conditions, providing a strong guarantee for obtaining reliable coolant recommended flow timing information and coolant recommended pressure timing information, which helps to improve the temperature stability during wafer cutting, reduce the impact of temperature fluctuations on chip quality, and improve the overall process level of semiconductor manufacturing.

[0039] Step S554, perform mean analysis on the centralized cooling samples to obtain the recommended coolant flow time series information and the recommended coolant pressure time series information. Specifically, for the extracted centralized cooling samples, perform mean calculation on the coolant flow record time series data and the coolant pressure record time series data. When calculating the mean, since each cooling sample contains the coolant flow and pressure data at different time points during the cutting process, it is necessary to average these time series data point by point. For example, for the centralized cooling sample set Samples, The coolant flow time series data of samples is (in represents time), then at a certain moment Average coolant flow rate The formula can be Calculated. Similarly, for the coolant pressure time series data, a similar method is used to calculate the mean. After such mean calculation, a set of coolant recommended flow time series information and a set of coolant recommended pressure time series information are obtained. These recommended information reflects the optimal change trend of coolant flow and pressure under normal cooling conditions as the cutting process proceeds, and can provide accurate control parameters for the actual wafer cutting cooling control system, so that it can dynamically adjust the coolant flow and pressure according to the real-time situation of the cutting process, ensure that the cutting temperature is always maintained within the appropriate range, improve the quality and stability of wafer cutting, reduce chip defects and material damage caused by temperature problems, provide a high-quality wafer foundation for subsequent semiconductor manufacturing processes, and improve the production efficiency and economic benefits of the entire semiconductor manufacturing process. At the same time, it also provides data support and theoretical basis for the optimization and improvement of cooling control strategies, which is helpful to further improve the energy utilization efficiency and process control level in the semiconductor manufacturing process.

[0040] In a possible implementation, when the number of samples in the cooling sample set is greater than the cooling sample number threshold, the cooling sample set is distributed in a two-dimensional virtual coordinate system according to the coolant flow recording time series data and the coolant pressure recording time series data, and step S540 further includes step S544, when the number of samples in the cooling sample set is less than or equal to the cooling sample number threshold, return to update the cutting speed timing information and the cutting depth timing information to execute the loop. Specifically, the number of samples in the current cooling sample set is determined and compared with the preset cooling sample number threshold. This threshold is determined by comprehensively considering factors such as the complexity of the subsequent data analysis model, the accuracy of the coolant parameter optimization, past experience, and the degree of grasp of the cutting variable relationship. If the number of samples is less than or equal to the threshold, it means that the data is insufficient to support subsequent operations, and it is necessary to return to update the cutting speed timing information and the cutting depth timing information. For cutting speed, based on experience and theoretical analysis, the range of values ​​is appropriately expanded, such as from [500,1000] mm per minute to [300,1200] mm, and the interval of values ​​is refined from 100 mm / minute to 50 mm / minute; for cutting depth, similarly, such as adjusting from [0.1,0.5] mm to [0.05,0.6] mm, the interval is refined from 0.1 mm to 0.05 mm, to enrich the data changes. Then, the loop is executed again, and the wafer cutting experiment is repeated based on the updated parameters. Data such as coolant and cutting temperature are recorded to form new samples to be added to the collection. After that, the number of samples is compared with the threshold, and the cycle is repeated until the number of samples exceeds the threshold, thereby providing sufficient and reliable data basis for the subsequent acquisition of the recommended coolant flow timing information and the recommended coolant pressure timing information, realizing effective optimization of cooling control, and ensuring cutting quality and efficiency.

[0041] Step S600, wafer cutting is performed according to the cutting speed timing information, the cutting depth timing information, the coolant recommended flow timing information and the coolant recommended pressure timing information, and a number of separated chips are obtained for MOSFET co-linear integrated packaging. Specifically, the cutting speed timing information is analyzed, and the cutting equipment speed control system is adjusted to make it move according to the predetermined speed curve; the cutting depth timing information is studied, and the cutting equipment depth control parameters are accurately set to ensure that the cutting depth accurately follows the predetermined changes. The coolant recommended flow and pressure timing information are input into the cooling control system, and the coolant supply system is debugged and calibrated to spray the coolant to the cutting area stably and accurately. Then the wafer cutting equipment is started, and the cutting tool cuts the wafer according to the preset speed and depth timing, and the coolant is cooled synchronously. After completion, the chips are carefully separated and the quality is strictly tested, including dimensional accuracy, surface quality and electrical performance. Qualified chips are integrated according to the MOSFET co-linear packaging process flow, and after operations such as patching, wire bonding, and potting, strictly follow the process standards and quality control requirements to ensure that high-quality and high-performance products are finally produced to meet market demand and promote industrial development.

[0042] In the above, refer to Figure 1 A MOSFET co-linear packaging control method according to an embodiment of the present invention is described in detail. Figure 2 A MOSFET co-line packaging control system according to an embodiment of the present invention is described.

[0043] A MOSFET co-linear packaging control system according to an embodiment of the present invention is used to solve the technical problems of inaccurate temperature control and low cooling efficiency in the wafer cutting process in the prior art, and achieves the technical effect of improving the accuracy of temperature control and cooling efficiency in the wafer cutting process. A MOSFET co-linear packaging control system includes: a chip distribution frame line diagram acquisition module 10, a cutting shortest path optimization module 20, a timing information acquisition module 30, a cutting temperature timing information acquisition module 40, a cooling control optimization module 50, and a wafer cutting module 60.

[0044] The chip distribution frame diagram acquisition module 10 is used to obtain the chip distribution frame diagram of the wafer to be cut.

[0045] The cutting shortest path optimization module 20 is used to optimize the cutting shortest path according to the chip distribution frame diagram to obtain a recommended wafer cutting path.

[0046] The timing information acquisition module 30 is used to obtain cutting speed timing information and cutting depth timing information.

[0047] The cutting temperature timing information acquisition module 40 is used to process the wafer cutting recommended path, the cutting speed timing information and the cutting depth timing information through a cutting temperature prediction model to obtain cutting temperature timing information.

[0048] The cooling control optimization module 50 is used to optimize the cooling control according to the cutting temperature timing information, and obtain the coolant recommended flow timing information and the coolant recommended pressure timing information.

[0049] The wafer cutting module 60 is used to cut the wafer according to the cutting speed timing information, the cutting depth timing information, the coolant recommended flow timing information and the coolant recommended pressure timing information to obtain a plurality of separated chips for MOSFET co-line integration packaging.

[0050] The specific configuration of the cutting temperature timing information acquisition module 40 will be described in detail below. As described above, the recommended wafer cutting path, the cutting speed timing information and the cutting depth timing information are processed through the cutting temperature prediction model to obtain the cutting temperature timing information. The cutting temperature timing information acquisition module 40 further includes: a wafer cutting equipment parameter acquisition unit, the wafer cutting equipment parameter acquisition unit is used to obtain the wafer cutting equipment parameters, wherein the wafer cutting equipment parameters include the cutting road structure parameters, the cutting groove structure parameters, the connecting rib structure parameters, and the cutting machine precision parameters; a cutting temperature prediction model construction unit, the cutting temperature prediction model construction unit is used to construct the cutting temperature prediction model with the cutting road structure parameters, the cutting groove structure parameters, the connecting rib structure parameters, and the cutting machine precision parameters as constraints; a cutting temperature timing information acquisition unit, the cutting temperature timing information acquisition unit is used to process the recommended wafer cutting path, the cutting speed timing information and the cutting depth timing information through the cutting temperature prediction model to obtain the cutting temperature timing information.

[0051] Wherein, the cutting temperature prediction model is constructed with the cutting path structure parameters, the cutting groove structure parameters, the connecting rib structure parameters and the cutting machine precision parameters as constraints, and the cutting temperature prediction model construction unit further includes: a similarity threshold configuration subunit, the similarity threshold configuration subunit is used to configure the cutting path structure similarity threshold, the cutting groove structure similarity threshold, the connecting rib structure similarity threshold and the cutting machine precision deviation distance threshold; a first cutting sample acquisition subunit, the first cutting sample acquisition subunit is used to obtain a first cutting sample, wherein the first cutting sample has a cutting path structure label, a cutting groove structure label, a connecting rib structure label and a cutting machine precision label; a similarity acquisition subunit, the similarity acquisition subunit is used to compare the cutting path structure label, the cutting groove structure label, the connecting rib structure label and the cutting machine precision label with the cutting path structure parameters, the cutting groove structure parameters, the connecting rib structure label and the cutting machine precision label. The cutting groove structure parameters, the connecting rib structure parameters, the cutting machine precision parameters, obtain the cutting path structure similarity, the cutting groove structure similarity, the connecting rib structure similarity and the cutting machine precision deviation distance; the sample set construction subunit, the sample set construction subunit is used to add the first cutting sample into the cutting temperature prediction model to construct the sample set when the cutting path structure similarity is greater than or equal to the cutting path structure similarity threshold, and the cutting groove structure similarity is greater than or equal to the cutting groove structure similarity threshold, the connecting rib structure similarity is greater than or equal to the connecting rib structure similarity threshold, and the cutting machine precision deviation distance is less than or equal to the cutting machine precision deviation distance threshold; the cutting temperature prediction model training subunit, the cutting temperature prediction model training subunit is used to train the cutting temperature prediction model when the cutting temperature prediction model construction sample set is greater than or equal to the preset sample number.

[0052] The specific configuration of the cooling control optimization module 50 will be described in detail below. As described above, the cooling control is optimized according to the cutting temperature timing information to obtain the recommended coolant flow timing information and the recommended coolant pressure timing information. The cooling control optimization module 50 further includes: an ambient temperature monitoring value acquisition unit, the ambient temperature monitoring value acquisition unit is used to obtain the ambient temperature monitoring value; a wafer cutting equipment parameter composition unit, the wafer cutting equipment parameter composition unit is used to obtain the wafer cutting equipment parameters, wherein the wafer cutting equipment parameters include cutting path structure parameters, cutting groove structure parameters, connecting rib structure parameters, and cutting machine precision parameters; a cooling sample set acquisition unit, the cooling sample set acquisition unit is used to obtain the cutting path structure parameters, the cutting groove structure parameters, the connecting rib structure parameters, and the cutting machine precision parameters. The structural parameters, the cutting machine precision parameters, and the cutting temperature timing information are used as constraints to collect cooling samples and obtain a cooling sample set, wherein any cooling sample has coolant flow recording timing data and coolant pressure recording timing data; a coordinate system distribution unit, wherein the coordinate system distribution unit is used to distribute the cooling sample set in a two-dimensional virtual coordinate system according to the coolant flow recording timing data and the coolant pressure recording timing data when the number of samples in the cooling sample set is greater than a cooling sample number threshold; a center point sorting unit, wherein the center point sorting unit is used to perform center point sorting according to the two-dimensional virtual coordinate system to obtain the coolant recommended flow timing information and the coolant recommended pressure timing information.

[0053] Among them, when the number of samples in the cooling sample set is greater than the cooling sample number threshold, the cooling sample set is distributed in a two-dimensional virtual coordinate system according to the coolant flow record timing data and the coolant pressure record timing data, and the coordinate system distribution unit further includes: a first coordinate axis construction subunit, the first coordinate axis construction subunit is used to construct a first coordinate axis with normalized data of coolant flow; a second coordinate axis construction subunit, the second coordinate axis construction subunit is used to construct a second coordinate axis with normalized data of coolant pressure; a virtual coordinate system configuration subunit, the virtual coordinate system configuration subunit is used to configure the two-dimensional virtual coordinate system according to the first coordinate axis and the second coordinate axis.

[0054] Among them, center point sorting is performed according to the two-dimensional virtual coordinate system to obtain the coolant recommended flow timing information and the coolant recommended pressure timing information, and the center point sorting unit further includes: a distribution coordinate set acquisition subunit, the distribution coordinate set acquisition subunit is used to obtain the cooling sample distribution coordinate set of the cooling sample set; an outlier analysis subunit, the outlier analysis subunit is used to perform LOF outlier analysis on the cooling sample distribution coordinate set to obtain a cooling sample outlier factor set; a centralized cooling sample extraction subunit, the centralized cooling sample extraction subunit is used to extract centralized cooling samples that are less than or equal to the outlier factor threshold in the cooling sample outlier factor set; a mean analysis subunit, the mean analysis subunit is used to perform mean analysis on the centralized cooling samples to obtain the coolant recommended flow timing information and the coolant recommended pressure timing information.

[0055] Among them, when the number of samples in the cooling sample set is greater than the cooling sample number threshold, the cooling sample set is distributed in a two-dimensional virtual coordinate system according to the coolant flow record timing data and the coolant pressure record timing data, and the coordinate system distribution unit further includes: an execution loop subunit, and the execution loop subunit is used to return to update the cutting speed timing information and the cutting depth timing information execution loop when the number of samples in the cooling sample set is less than or equal to the cooling sample number threshold.

[0056] A MOSFET co-linear packaging control system provided in an embodiment of the present invention can execute a MOSFET co-linear packaging control method provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0057] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0058] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A MOSFET co-linear packaging control method, characterized in that: include: Obtain a chip distribution frame diagram of the wafer to be cut; Optimize the shortest cutting path according to the chip distribution frame diagram to obtain a recommended wafer cutting path; Obtaining cutting speed timing information and cutting depth timing information; The wafer cutting recommended path, the cutting speed timing information and the cutting depth timing information are processed by a cutting temperature prediction model to obtain cutting temperature timing information; Optimizing the cooling control according to the cutting temperature timing information to obtain the recommended coolant flow timing information and the recommended coolant pressure timing information; Wafer cutting is performed according to the cutting speed timing information, the cutting depth timing information, the coolant recommended flow timing information and the coolant recommended pressure timing information to obtain a plurality of separate chips for MOSFET co-linear integration packaging.

2. The method according to claim 1, characterized in that The wafer cutting recommended path, the cutting speed information and the cutting depth timing information are processed by a cutting temperature prediction model to obtain cutting temperature timing information, including: Obtaining wafer cutting equipment parameters, wherein the wafer cutting equipment parameters include cutting road structure parameters, cutting groove structure parameters, connecting rib structure parameters, and cutting machine precision parameters; The cutting temperature prediction model is constructed with the cutting path structural parameters, the cutting groove structural parameters, the connecting rib structural parameters, and the cutting machine precision parameters as constraints; The wafer cutting recommended path, the cutting speed timing information and the cutting depth timing information are processed by a cutting temperature prediction model to obtain cutting temperature timing information.

3. The method according to claim 2, characterized in that The cutting temperature prediction model is constructed with the cutting path structural parameters, the cutting groove structural parameters, the connecting rib structural parameters, and the cutting machine precision parameters as constraints, including: Configure the cutting path structure similarity threshold, cutting groove structure similarity threshold, connecting rib structure similarity threshold and cutting machine accuracy deviation distance threshold; Obtaining a first cutting sample, wherein the first cutting sample has a cutting track structure label, a cutting groove structure label, a connecting rib structure label, and a cutting machine precision label; Compare the cutting path structure label, the cutting groove structure label, the connecting rib structure label, and the cutting machine precision label with the cutting path structure parameters, the cutting groove structure parameters, the connecting rib structure parameters, and the cutting machine precision parameters to obtain the cutting path structure similarity, the cutting groove structure similarity, the connecting rib structure similarity, and the cutting machine precision deviation distance; When the cutting road structure similarity is greater than or equal to the cutting road structure similarity threshold, the cutting groove structure similarity is greater than or equal to the cutting groove structure similarity threshold, the connecting rib structure similarity is greater than or equal to the connecting rib structure similarity threshold, and the cutting machine precision deviation distance is less than or equal to the cutting machine precision deviation distance threshold, the first cutting sample is added into the cutting temperature prediction model to construct the sample set; When the cutting temperature prediction model construction sample set is greater than or equal to the preset sample number, the cutting temperature prediction model is trained.

4. The method according to claim 1, characterized in that Optimizing the cooling control according to the cutting temperature timing information to obtain the coolant recommended flow timing information and the coolant recommended pressure timing information, including: Get the ambient temperature monitoring value; Obtaining wafer cutting equipment parameters, wherein the wafer cutting equipment parameters include cutting road structure parameters, cutting groove structure parameters, connecting rib structure parameters, and cutting machine precision parameters; Cooling samples are collected with the cutting path structural parameters, the cutting groove structural parameters, the connecting rib structural parameters, the cutting machine precision parameters, and the cutting temperature timing information as constraints to obtain a cooling sample set, wherein any cooling sample has coolant flow recording timing data and coolant pressure recording timing data; When the number of samples of the cooling sample set is greater than a cooling sample number threshold, distributing the cooling sample set in a two-dimensional virtual coordinate system according to the coolant flow recording time series data and the coolant pressure recording time series data; The center points are sorted according to the two-dimensional virtual coordinate system to obtain the coolant recommended flow time series information and the coolant recommended pressure time series information.

5. The method according to claim 4, characterized in that According to the coolant flow recording time series data and the coolant pressure recording time series data, the cooling sample set is distributed in a two-dimensional virtual coordinate system, including: The first coordinate axis is constructed using the normalized data of the coolant flow rate; The second coordinate axis is constructed using the normalized data of the cooling fluid pressure; The two-dimensional virtual coordinate system is configured according to the first coordinate axis and the second coordinate axis.

6. The method according to claim 4, characterized in that The center point is sorted according to the two-dimensional virtual coordinate system to obtain the coolant recommended flow time series information and the coolant recommended pressure time series information, including: Obtaining a cooling sample distribution coordinate set of the cooling sample set; Performing LOF outlier analysis on the cooling sample distribution coordinate set to obtain a cooling sample outlier factor set; Extracting concentrated cooling samples whose outlier factors are less than or equal to the outlier factor threshold value from the cooling sample outlier factor set; The centralized cooling samples are subjected to mean analysis to obtain the coolant recommended flow time series information and the coolant recommended pressure time series information.

7. The method according to claim 4, characterized in that Also includes: When the sample quantity of the cooling sample set is less than or equal to the cooling sample quantity threshold, the loop is executed by returning to update the cutting speed timing information and the cutting depth timing information.

8. A MOSFET co-line packaging control system, characterized in that: The system is used to implement a MOSFET co-linear packaging control method according to any one of claims 1 to 7, and the system comprises: A chip distribution frame diagram acquisition module, wherein the chip distribution frame diagram acquisition module is used to obtain a chip distribution frame diagram of a wafer to be cut; A cutting shortest path optimization module, wherein the cutting shortest path optimization module is used to optimize the cutting shortest path according to the chip distribution frame line diagram to obtain a wafer cutting recommended path; A timing information acquisition module, wherein the timing information acquisition module is used to obtain cutting speed timing information and cutting depth timing information; A cutting temperature timing information acquisition module, wherein the cutting temperature timing information acquisition module is used to process the wafer cutting recommended path, the cutting speed timing information and the cutting depth timing information through a cutting temperature prediction model to obtain cutting temperature timing information; A cooling control optimization module, the cooling control optimization module is used to optimize the cooling control according to the cutting temperature timing information, and obtain the coolant recommended flow timing information and the coolant recommended pressure timing information; A wafer cutting module is used to cut wafers according to the cutting speed timing information, the cutting depth timing information, the coolant recommended flow timing information and the coolant recommended pressure timing information to obtain a plurality of separate chips for MOSFET co-linear integration packaging.

Images