A method, system, and storage device for chip soldering

Abstract

The present application provides a method, a system, and a storage device for chip soldering. By obtaining a soldering pressure data set, dividing the soldering pressure data into multiple discrete pressure data segments through the discrete features of the soldering pressure data set, further determining the pressure deviation coefficient of the target chip, obtaining the pre-soldering image of the target chip, and then extracting the distribution vector of the solder joints of the target chip pins from the pre-soldering image, determining the torch offset amount during the soldering of the target chip through the pressure deviation coefficient and the distribution vector of the solder joints, thereby determining the argon gas flow domain of each solder joint of the target chip pins, and further determining the flow compensation value of each pin of the target chip, so as to determine the variable solder amount at different positions of the target chip pins according to all the flow compensation values and the torch offset amount, and heating and soldering each pin of the target chip through all the variable solder amounts, the dynamic adjustment of the solder amount during the chip soldering process can be realized.

Description

Technical Field

[0001] The present application relates to the field of welding technology. More specifically, the present application relates to a method, a system, and a storage device for chip welding. Background Art

[0002] Welding technology is a process of melting metal or non-metal materials by heating them to a high temperature, making part or all of them molten, and using the molten material to fill or not fill the gap, so that the materials form a dense connection after cooling. It is an important manufacturing process and is widely used in various fields such as construction, aerospace, automotive manufacturing, and electronic equipment in the engineering field. There are different types of welding methods in welding technology, including arc welding, gas shielded welding, laser welding, plasma welding, etc. Each method has its applicable occasions and characteristics. The application of welding technology can not only achieve the connection of materials, but also carry out repair, improvement, and processing, providing important technical support for all walks of life.

[0003] Chip welding is a key process connection technology in electronic manufacturing. By connecting tiny chips to a circuit board, signal transmission is achieved. This technology involves precisely fusing the pins of the chip with the pads on the circuit board. This fusion method usually requires completing the welding process in a high-temperature environment. However, during the chip welding process, the input amount of solder affects the chip welding quality. Excessive solder will cause short circuits between welding positions, and insufficient solder will cause cold welding (the cold welding phenomenon means that the solder does not fully wet the welding surface, resulting in poor welding contact). Therefore, how to achieve dynamic adjustment of the solder amount during the chip welding process to improve the chip welding quality has become a difficult problem faced by the industry. Summary of the Invention

[0004] The present application provides a method, a system, and a storage device for chip welding, which can achieve dynamic adjustment of the solder amount during the chip welding process.

[0005] In a first aspect, the present application provides a method for chip welding, including the following steps:

[0006] Start chip welding and obtain the welding pressure data set during the historical welding of chips;

[0007] Divide the welding pressure data into multiple discrete pressure data segments through the discrete characteristics of the welding pressure data set, and determine the pressure deviation coefficient of the target chip according to all the discrete pressure data segments;

[0008] Obtain the pre-welding image of the target chip, and extract the distribution vector of the solder joints of the target chip pins from the pre-welding image based on a pre-trained solder joint feature model;

[0009] Determine the torch offset during the welding of the target chip based on the pressure deviation coefficient and the distribution vector of the solder joints to be welded;

[0010] Based on the argon gas flow rate data set during the welding of historical chips and the distribution vector of the solder joints to be welded, determine the argon gas flow rate domains for each solder joint of the pins of the target chip, and then determine the flow compensation values for each pin of the target chip according to all the argon gas flow rate domains;

[0011] Thus, determine the variable solder amounts at different positions of the pins of the target chip according to all the flow compensation values and the torch offset, and heat and weld each pin of the target chip with all the variable solder amounts.

[0012] In some embodiments, dividing the welding pressure data into multiple discrete pressure data segments by the discrete features of the welding pressure data set specifically includes:

[0013] Determine multiple welding pressure change rate sequences according to the welding pressure data set;

[0014] Determine the discrete features of the welding pressure data set through all the welding pressure change rate sequences;

[0015] Determine the feature division coefficient of the welding pressure data set according to the discrete features;

[0016] Divide the welding pressure data set into multiple discrete pressure data segments by the feature division coefficient.

[0017] In some embodiments, determining the pressure deviation coefficient of the target chip according to all the discrete pressure data segments specifically includes:

[0018] Determine the pressure extreme value difference of each discrete pressure data segment;

[0019] Determine the welding pressure equilibrium value of the target chip according to the welding pressure data set;

[0020] Determine the pressure deviation coefficient of the target chip through all the pressure extreme value differences and the welding pressure equilibrium value.

[0021] In some embodiments, extracting the distribution vector of the solder joints of the pins of the target chip from the pre-welding image based on a pre-trained solder joint feature model specifically includes:

[0022] Obtain the historical pre-welding image set of chips of the same type as the target chip;

[0023] Train a solder joint feature model based on the historical pre-welding image set;

[0024] Feature extraction is performed on the pre-welding image of the target chip using the solder joint feature model to obtain the solder joint distribution vector of the pins of the target chip.

[0025] In some embodiments, determining the argon gas flow domain of each solder joint of the pins of the target chip based on the argon gas flow dataset during historical chip welding and the solder joint distribution vector specifically includes:

[0026] Obtain the argon gas flow dataset during historical chip welding;

[0027] Extract the argon gas flow sequence from the argon gas flow dataset;

[0028] Select the first argon gas flow from the argon gas flow sequence;

[0029] Determine the upper bound and lower bound of the argon gas flow of the solder joint of the pins of the target chip corresponding to this argon gas flow through the solder joint distribution vector;

[0030] Take the range composed of the upper bound and lower bound of the argon gas flow as the argon gas flow domain of the solder joint of the pins of the target chip corresponding to this argon gas flow.

[0031] Continue to determine the argon gas flow domain of the solder joint of the pins of the target chip corresponding to the remaining argon gas flows in the argon gas flow sequence.

[0032] In some embodiments, determining the flow compensation value of each pin of the target chip according to all the argon gas flow domains specifically includes:

[0033] Determine the flow compensation margin of the target chip according to all the argon gas flow domains;

[0034] Determine the flow compensation value of each pin of the target chip through the flow compensation margin.

[0035] In some embodiments, determining the variable solder amount at different positions of the pins of the target chip according to all the flow compensation values and the torch offset specifically includes:

[0036] Determine the solder adjustment coefficient at different positions of the pins of the target chip according to all the flow compensation values and the torch offset;

[0037] Determine the variable solder amount at different positions of the pins of the target chip through all the solder adjustment coefficients and the preset solder equalization amount.

[0038] In a second aspect, the present application provides a chip welding system, including:

[0039] An acquisition module, configured to acquire the welding pressure dataset during historical chip welding after starting chip welding;

[0040] A processing module, configured to divide the welding pressure data into multiple discrete pressure data segments through the discrete features of the welding pressure data set, and determine the pressure deviation coefficient of the target chip according to all the discrete pressure data segments;

[0041] The processing module is further configured to obtain a pre-welding image of the target chip, and extract a solder joint distribution vector of the pins of the target chip from the pre-welding image based on a pre-trained solder joint feature model;

[0042] The processing module is further configured to determine the torch offset amount during welding of the target chip through the pressure deviation coefficient and the solder joint distribution vector;

[0043] The processing module is further configured to determine the argon gas flow domains of the respective solder joints of the pins of the target chip based on the argon gas flow data set during historical chip welding and the solder joint distribution vector, and then determine the flow compensation values of the respective pins of the target chip according to all the argon gas flow domains;

[0044] An execution module, configured to determine the variable solder amounts at different positions of the pins of the target chip according to all the flow compensation values and the torch offset amount, and heat-weld the respective pins of the target chip through all the variable solder amounts.

[0045] In a third aspect, the present application provides a computer device, which includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the above-mentioned chip welding method.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned chip welding method is implemented.

[0047] The technical solutions provided by the embodiments disclosed in the present application have the following beneficial effects:

[0048] In the method, system, and storage device for chip soldering provided by this application, first, start chip soldering, obtain the welding pressure data set during historical chip soldering, divide the welding pressure data into multiple discrete pressure data segments through the discrete features of the welding pressure data set, determine the pressure deviation coefficient of the target chip according to all the discrete pressure data segments, obtain the pre-soldering image of the target chip, extract the distribution vector of the solder joints to be welded of the target chip pins from the pre-soldering image based on a pre-trained solder joint feature model, determine the torch offset during target chip soldering through the pressure deviation coefficient and the distribution vector of the solder joints to be welded, determine the argon gas flow domain of each solder joint to be welded of the target chip pins based on the argon gas flow data set during historical chip soldering and the distribution vector of the solder joints to be welded, and then determine the flow compensation value of each pin of the target chip according to all the argon gas flow domains, so as to determine the variable solder amount at different positions of the target chip pins according to all the flow compensation values and the torch offset, and heat-solder each pin of the target chip through all the variable solder amounts.

[0049] Thus, first, determine the pressure deviation coefficient of the target chip according to all the discrete pressure data segments, where the pressure deviation coefficient reflects the fluctuating change of pressure during chip soldering, and then use the pressure deviation coefficient to measure the torch offset during target chip soldering; second, determine the maximum and minimum values that can be used for the argon gas flow of each solder joint to be welded of the target chip pins through the argon gas flow data set, so as to limit the argon gas flow range (i.e., argon gas flow domain) of the solder joints to be welded on each pin of the target chip, and then quantify each argon gas flow domain to obtain the flow compensation value that can be used to compensate the argon gas flow of the target chip pins; then, comprehensively determine the amount of solder to be used for each solder joint to be welded of each target chip pin by the torch offset and the flow compensation value of the target chip pins, avoiding the adverse effects caused by excessive or insufficient use of the solder amount, and then realizing the dynamic adjustment of the solder amount during chip soldering, thereby improving the chip soldering quality. Description of the Drawings

[0050] Figure 1 is an exemplary flowchart of the method for chip soldering shown in some embodiments of this application;

[0051] Figure 2 is a schematic flowchart of determining the distribution vector of the solder joints to be welded in some embodiments of this application;

[0052] Figure 3 is a schematic flowchart of determining the variable solder amount in some embodiments of this application;

[0053] Figure 4 is a structural block diagram of the chip soldering system in some embodiments of this application;

[0054] Figure 5 It is a schematic structural diagram of a computer device for implementing a method of chip soldering as shown in some embodiments of the present application. Detailed implementation manners

[0055] The core of the present application is to start chip soldering, obtain a welding pressure data set during historical chip soldering, divide the welding pressure data into multiple discrete pressure data segments through the discrete features of the welding pressure data set, determine the pressure deviation coefficient of the target chip according to all the discrete pressure data segments, obtain a pre-soldering image of the target chip, extract the distribution vector of solder joints to be soldered of the target chip pins from the pre-soldering image based on a pre-trained solder joint feature model, determine the torch offset during target chip soldering through the pressure deviation coefficient and the distribution vector of solder joints to be soldered, determine the argon gas flow domain of each solder joint to be soldered of the target chip pins based on the argon gas flow data set during historical chip soldering and the distribution vector of solder joints to be soldered, and then determine the flow compensation value of each pin of the target chip according to all the argon gas flow domains, so as to determine the variable solder amount at different positions of the target chip pins according to all the flow compensation values and the torch offset, and heat and solder each pin of the target chip through all the variable solder amounts, thereby realizing the dynamic adjustment of the solder amount during the chip soldering process.

[0056] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners. Refer to Figure 1 , this figure is an exemplary flowchart of a method of chip soldering as shown in some embodiments of the present application. The method 100 of chip soldering mainly includes the following steps:

[0057] In step 101, start chip soldering and obtain a welding pressure data set during historical chip soldering.

[0058] Specifically, after starting chip soldering, obtain a welding pressure data set during historical chip soldering from the database of the welding system of the target chip.

[0059] It should be noted that the welding pressure data set in the present application represents a set composed of multiple welding pressure data. The welding pressure data in the welding pressure data set represents a sequence of pressure values collected by a pressure sensor on the torch when welding each chip pin. When collecting, by fixing one chip pin, the pressure values applied by the torch on the chip pin are collected in a counterclockwise order. In addition, each welding pressure data in the welding pressure data set is the welding pressure data obtained when welding a standard-compliant chip.

[0060] In step 102, the welding pressure data is divided into multiple discrete pressure data segments according to the discrete features of the welding pressure data set, and the pressure deviation coefficient of the target chip is determined based on all the discrete pressure data segments.

[0061] In some embodiments, dividing the welding pressure data into multiple discrete pressure data segments according to the discrete features of the welding pressure data set can be implemented by the following steps:

[0062] Determine multiple welding pressure change rate sequences according to the welding pressure data set;

[0063] Determine the discrete features of the welding pressure data set through all the welding pressure change rate sequences;

[0064] Determine the feature division coefficient of the welding pressure data set according to the discrete features;

[0065] Divide the welding pressure data set into multiple discrete pressure data segments through the feature division coefficient.

[0066] In specific implementation, determining multiple welding pressure change rate sequences according to the welding pressure data set, that is: select a welding pressure data from the welding pressure data set, perform curve fitting on this welding pressure data, use the obtained curve as the pressure fitting curve of this welding pressure data, then calculate the derivative of the position corresponding to each welding pressure value in this welding pressure data in the pressure fitting curve, take all the obtained derivatives as the welding pressure change rates, arrange all the obtained welding pressure change rates in the order of the welding pressure values in this welding pressure data, and take the arranged sequence as the welding pressure change rate sequence of this welding pressure data, and continue to determine the welding pressure change rate sequences of the remaining welding pressure data in the welding pressure data set.

[0067] It should be noted that the curve fitting in this application can be implemented through different algorithms, such as polynomial fitting, least squares method, spline interpolation, etc. The purpose of curve fitting is to find the change trend between the welding pressure values in the welding pressure data.

[0068] In addition, it should be noted that the welding pressure change rate sequence in this application represents a sequence composed of the welding pressure change rates between adjacent welding pressure values in the welding pressure data. Each welding pressure change rate represents the pressure change rate between adjacent chip pins during the chip welding process. The stability of the welding pressure during chip welding can be measured through the welding pressure gradient sequence. The larger the welding pressure change rate, the worse the stability of the welding pressure.

[0069] In specific implementation, the discrete features of the welding pressure data set are determined through all sequences of welding pressure change rates, that is: the discrete features represent the normalized values of the overall discrete degree of the sequences of welding pressure change rates of each welding pressure data in the welding pressure data set. In some embodiments, the mean value of the variances of each sequence of welding pressure gradients can be used as the normalized value of the discrete degree of the welding pressure data set.

[0070] In specific implementation, the feature division coefficient of the welding pressure data set is determined according to the discrete features, that is: taking the negative exponential power with base e of the discrete features, and using the value obtained after taking the negative exponential power as the feature division coefficient of the welding pressure data set, that is: the feature division coefficient is , being the discrete feature.

[0071] It should be noted that in this application, the feature division coefficient represents the coefficient for dividing the welding pressure data set, and different welding pressure data with different discrete features can be distinguished through the feature division coefficient.

[0072] In specific implementation, the welding pressure data set is divided into multiple discrete pressure data segments through the feature division coefficient, that is: first, multiplying the feature division coefficient by 0.5, and using the obtained value as the feature division center coefficient. Then, for each welding pressure data in the welding pressure data set, after obtaining the discrete feature, taking the negative exponential power, and using the value obtained after taking the negative exponential power as the discrete feature coefficient of the corresponding welding pressure data. All welding pressure data with discrete feature coefficients less than or equal to the feature division center coefficient are divided into the same part, and the welding pressure data constituting this part is used as a discrete pressure data segment. All welding pressure data with discrete feature coefficients greater than the feature division center coefficient and less than or equal to the feature division coefficient are divided into the same part, and the welding pressure data constituting this part is used as a discrete pressure data segment. All welding pressure data with discrete feature coefficients greater than the feature division coefficient are divided into the same part, and the welding pressure data constituting this part is used as a discrete pressure data segment.

[0073] It should be noted that in this application, the discrete pressure data segment represents the welding pressure data composed of the same pressure abnormal fluctuations. Combining the welding pressure data with the same pressure abnormal fluctuations together can more easily detect the change of abnormal welding pressure values on the chip pins.

[0074] In some embodiments, the pressure deviation coefficient of the target chip can be determined according to all the discrete pressure data segments through the following steps:

[0075] Determine the pressure extreme difference of each discrete pressure data segment;

[0076] Determine the welding pressure equilibrium value of the target chip according to the welding pressure data set;

[0077] Determine the pressure deviation coefficient of the target chip through all the pressure extreme differences and the welding pressure equilibrium value.

[0078] Specifically, when implemented, determine the pressure extreme difference of each discrete pressure data segment, that is: select the maximum welding pressure value and the minimum welding pressure value from each discrete pressure data segment, subtract the minimum welding pressure value from the maximum welding pressure value, and use the obtained value as the pressure extreme difference of the corresponding discrete pressure data segment; determine the welding pressure equilibrium value of the target chip according to the welding pressure data set, that is: calculate the average value of all the welding pressure values in the welding pressure data set, and use the obtained average value as the welding pressure equilibrium value of the target chip.

[0079] In this application, the pressure extreme difference can be used to measure the data volatility of the discrete pressure data segment. The greater the pressure extreme difference, the greater the data volatility of the discrete pressure data segment.

[0080] Specifically, when implemented, determine the pressure deviation coefficient of the target chip through all the pressure extreme differences and the welding pressure equilibrium value, that is: calculate the average value of all the pressure extreme differences and then divide it by the welding pressure equilibrium value, and use the obtained value as the pressure deviation coefficient of the target chip.

[0081] It should be noted that the pressure deviation coefficient in this application reflects the fluctuating change of the pressure during the chip welding process. If the pressure deviation coefficient is smaller, it means that the pressure change during the chip welding process is small, and the chip welding quality is relatively stable. If the pressure deviation coefficient is larger, it means that there is a large pressure fluctuation during the chip welding process, and the chip welding quality is unstable.

[0082] In step 103, obtain the pre-welding image of the target chip, and extract the distribution vector of the solder joints to be welded of the pins of the target chip from the pre-welding image based on the pre-trained solder joint feature model.

[0083] Specifically, when implemented, photograph the target chip through a microscopic camera, and use the obtained image as the pre-welding image of the target chip.

[0084] It should be noted that the pre-welding image in this application is the image when the target chip is accurately placed on the solder pad of the printed circuit board (PCB) for pre-welding preparation. In addition, the type of the target chip belongs to the surface mount technology chip type, specifically including: integrated circuit chips, capacitor chips, crystal oscillator chips, memory chips, etc.

[0085] In some embodiments, refer to Figure 2As shown, this figure is a schematic flowchart of determining the distribution vector of solder joints to be welded in some embodiments of the present application. In this embodiment, the distribution vector of solder joints to be welded of the target chip pins is extracted from the pre-welding image based on a pre-trained solder joint feature model, which can be implemented by the following steps:

[0086] First, in step 1031, obtain a historical pre-welding image set of chips of the same type as the target chip;

[0087] Secondly, in step 1032, train a solder joint feature model based on the historical pre-welding image set;

[0088] Then, in step 1033, use the solder joint feature model to extract features from the pre-welding image of the target chip to obtain the distribution vector of solder joints to be welded of the target chip pins.

[0089] Specifically, when implementing, obtain a historical pre-welding image set of chips of the same type as the target chip, that is: obtain multiple historical pre-welding images of chips of the same type as the target chip from the database of the chip welding system, and use the set composed of the multiple historical pre-welding images as the historical pre-welding image set.

[0090] It should be noted that the historical pre-welding images in the present application are images marked with detailed information, where the detailed information includes: the position coordinates, area, etc. of each solder joint to be welded of the chip pins, and the detailed information is composed into a vector, that is: each historical pre-welding image corresponds to a vector.

[0091] Specifically, when implementing, train a solder joint feature model based on the historical pre-welding image set, that is: first preprocess the historical pre-welding image set, and the preprocessing includes: Gaussian filtering, perspective transformation, histogram equalization, etc. Gaussian filtering is mainly to remove the influence of noise, perspective transformation is mainly to correct the perspective distortion caused by the position deviation between the chip placement position and the camera, histogram equalization is mainly to improve the contrast between the target area and the surrounding area of the pre-welding image. Then, divide the historical pre-welding image set into a pre-welding image training set and a pre-welding image validation set according to the ratios of 70% and 30% respectively, ensure that the pre-welding image samples in each data set are evenly distributed, use the pre-welding image training set to train the residual neural network, optimize the parameters of the residual neural network through the backpropagation algorithm, use the pre-welding image validation set to monitor the training process, and adjust the hyperparameters of the residual neural network according to the pre-welding image validation set, such as: learning rate, batch size, etc. Finally, use the residual neural network model after the training is completed as the solder joint feature model.

[0092] It should be noted that the solder joint feature model in the present application represents a model for extracting the feature information of solder joints to be welded of chip pins in the pre-welding image of surface mount technology type chips.

[0093] In specific implementation, the pre-welding image of the target chip is subjected to feature extraction using the to-be-welded point feature model to obtain the to-be-welded point distribution vector of the pins of the target chip, that is: the pre-welding image of the target chip is subjected to the same preprocessing as the above operations, the preprocessed image is used as the input image, the to-be-welded point feature model is used to perform forward propagation on the input image, and the vector obtained by the forward propagation is used as the to-be-welded point distribution vector of the pins of the target chip.

[0094] It should be noted that the to-be-welded point distribution vector in this application is composed of multiple to-be-welded point components. The to-be-welded point components in the to-be-welded point distribution vector represent information such as the position coordinates and area of the to-be-welded points of the chip pins, and each to-be-welded point component corresponds to a to-be-welded point of a chip pin.

[0095] In step 104, the torch offset amount during welding of the target chip is determined through the pressure deviation coefficient and the to-be-welded point distribution vector.

[0096] In some embodiments, determining the torch offset amount during welding of the target chip through the pressure deviation coefficient and the to-be-welded point distribution vector can be implemented by the following steps:

[0097] Determine the adjacent distance between the to-be-welded points of the chip pins corresponding to each to-be-welded point component in the to-be-welded point distribution vector;

[0098] Determine the torch offset amount during welding of the target chip according to the pressure deviation coefficient and the adjacent distances of all the to-be-welded points of the chip pins.

[0099] In specific implementation, determining the adjacent distance between the to-be-welded points of the chip pins corresponding to each to-be-welded point component in the to-be-welded point distribution vector, that is: select a to-be-welded point component from the to-be-welded point distribution vector, calculate the distance according to the position coordinates of the to-be-welded point of the chip pin corresponding to this to-be-welded point component and the position coordinates of the to-be-welded points of the chip pins corresponding to the remaining to-be-welded point components, and use the sum of the distances between the two adjacent to-be-welded points of the chip pins adjacent to the to-be-welded point of the chip pin corresponding to this to-be-welded point component as the adjacent distance between the to-be-welded points of the chip pin corresponding to this to-be-welded point component, and continue to determine the adjacent distances between the to-be-welded points of the chip pins corresponding to the remaining to-be-welded point components in the to-be-welded point distribution vector.

[0100] In specific implementation, determining the torch offset amount during welding of the target chip according to the pressure deviation coefficient and the adjacent distances of all the to-be-welded points of the chip pins, that is: calculate the mean value of the adjacent distances of all the to-be-welded points of the chip pins, divide the pressure deviation coefficient by the obtained mean value, and use the value obtained by the division as the torch offset amount during welding of the target chip.

[0101] It should be noted that the torch offset in this application reflects the accuracy of the torch position during chip soldering. A more accurate torch position can ensure sufficient and uniform contact between the solder joints and the chip pins, thereby improving the chip soldering quality.

[0102] In step 105, based on the argon gas flow rate data set during historical chip soldering and the solder joint distribution vector, determine the argon gas flow rate domain for each solder joint of the target chip pins, and then determine the flow compensation value for each pin of the target chip based on all the argon gas flow rate domains.

[0103] In some embodiments, determining the argon gas flow rate domain for each solder joint of the target chip pins based on the argon gas flow rate data set during historical chip soldering and the solder joint distribution vector can be achieved by the following steps:

[0104] Obtain the argon gas flow rate data set during historical chip soldering;

[0105] Extract the argon gas flow rate sequence from the argon gas flow rate data set;

[0106] Select the first argon gas flow rate from the argon gas flow rate sequence;

[0107] Determine the upper bound and lower bound of the argon gas flow rate for the solder joints of the target chip pins corresponding to this argon gas flow rate through the solder joint distribution vector;

[0108] Take the range composed of the upper bound and the lower bound of the argon gas flow rate as the argon gas flow rate domain for the solder joints of the target chip pins corresponding to this argon gas flow rate.

[0109] Continue to determine the argon gas flow rate domain for the solder joints of the target chip pins corresponding to the remaining argon gas flow rates in the argon gas flow rate sequence.

[0110] Specifically, obtain the argon gas flow rate data set during historical chip soldering from the database of the chip soldering system.

[0111] It should be noted that the argon gas flow rate data set in this application represents a set composed of multiple argon gas flow rate data. Among them, the argon gas flow rate data in the argon gas flow rate data set represents the sequence of argon gas flow rates collected by the gas flow meter on the torch when soldering each chip pin. When collecting, by fixing one chip pin, the argon gas flow rates released on each chip pin are collected in a counterclockwise order. In addition, argon is usually used as a shielding gas to protect the soldering area from oxygen and water vapor in the air. By adjusting and controlling the argon gas flow rate, it can ensure that the soldering area is sufficiently protected.

[0112] Among them, in some embodiments, extracting the argon gas flow rate sequence from the argon gas flow rate data set can be achieved by the following steps:

[0113] Determine the argon flow distribution entropy of the argon flow data set;

[0114] Extract features from the argon flow data set through the argon flow distribution entropy to obtain an argon flow sequence.

[0115] When specifically implemented, determine the argon flow distribution entropy of the argon flow data set, that is: first, regard the numerical value in each argon flow data in the argon flow data set as a random variable, then use information entropy to calculate the entropy value of each argon flow data, and then calculate the mean value of the entropy values of all argon flow data, and take the obtained mean value as the argon flow distribution entropy of the argon flow data set. In some embodiments, the information entropy can be calculated in the form of cross entropy, and in other embodiments, other existing entropy calculation methods can also be used for calculation, which is not limited here.

[0116] It should be noted that the argon flow distribution entropy described in this application represents a measure of the uncertainty of the argon flow distribution in the argon flow data set. The higher the flow distribution entropy, the more random the distribution of the argon flow among different values, and the greater the difference between the flow values. While the lower the flow distribution entropy, it means that the argon flow is more concentrated near certain specific values, and the distribution is more concentrated and more certain.

[0117] When specifically implemented, extract features from the argon flow data set through the argon flow distribution entropy to obtain an argon flow sequence, that is: select the argon flow data with an entropy value greater than the argon flow distribution entropy from the argon flow data set, and then calculate the median of each argon flow data at the same position for the selected argon flow data, arrange all the medians in the order of collection, and take the arranged order as the argon flow sequence. For example: S1 = [2, 2, 3], S2 = [3, 2, 4], S3 = [4, 2, 5] are three selected argon flow data. The first positions in S1, S2, and S3 are 2, 3, and 4, so the median is 3. The second positions in S1, S2, and S3 are 2, 2, and 2, so the median is 2. The third positions in S1, S2, and S3 are 3, 4, and 5, so the median is 4. Therefore, the sequence arranged in the order of collection is [3, 2, 4].

[0118] It should be noted that the argon flow distribution sequence is a sequence composed of argon flow data selected according to the argon flow distribution entropy characteristics in the argon flow data set.

[0119] During specific implementation, the upper and lower bounds of the argon flow rate for the solder joints to be welded corresponding to the target chip pins are determined through the solder joint distribution vector of the argon flow rate, that is: the average value of all the argon flow rates in the argon flow rate sequence is calculated, and the obtained value is used as the argon flow rate equilibrium value. If the argon flow rate is greater than the argon flow rate equilibrium value, the argon flow rate is multiplied by the area of the chip pin corresponding to the solder joint component in the solder joint distribution vector, and the obtained product value is used as the upper bound of the argon flow rate for the solder joint of the chip pin corresponding to the solder joint component. If the argon flow rate is less than or equal to the argon flow rate equilibrium value, the argon flow rate equilibrium value is multiplied by the area of the chip pin corresponding to the solder joint component in the solder joint distribution vector, and the obtained product value is used as the lower bound of the argon flow rate for the solder joint of the chip pin corresponding to the solder joint component.

[0120] It should be noted that in this application, the argon flow rate range represents the range composed of the lower bound and the upper bound of the argon flow rate during the chip welding process. Among them, the lower bound of the argon flow rate represents the lowest allowable value of the argon flow rate on the chip pins during the welding process, and the upper bound of the argon flow rate represents the highest allowable value of the argon flow rate on the chip pins during the welding process. If the argon flow rate is lower than the lower bound of the argon flow rate, problems such as oxidation and hydrogen intrusion may occur due to insufficient protection of the welding area. If the argon flow rate exceeds the upper bound of the argon flow rate, problems such as gas flow disturbance and increased sputtering may occur, and at the same time, the argon consumption will also increase.

[0121] In some embodiments, determining the flow compensation value for each pin of the target chip according to all the argon flow rate ranges can be achieved by the following steps:

[0122] Determine the flow compensation margin of the target chip according to all the argon flow rate ranges;

[0123] Determine the flow compensation value for each pin of the target chip through the flow compensation margin.

[0124] During specific implementation, determining the flow compensation margin of the target chip according to all the argon flow rate ranges, that is: select the largest upper bound of the argon flow rate from all the argon flow rate ranges, select the smallest lower bound of the argon flow rate from all the argon flow rate ranges, subtract the smallest lower bound of the argon flow rate from the largest upper bound of the argon flow rate, and use the obtained difference value as the flow compensation margin of the target chip.

[0125] It should be noted that in this application, the flow compensation margin represents the additional margin reserved for controlling the argon flow rate during the chip welding process, and is used to measure the tolerance of the argon flow rate fluctuation during the chip welding process. The larger the flow compensation margin, the higher the tolerance of the argon flow rate fluctuation during the chip welding process.

[0126] In specific implementation, the flow compensation values of each pin of the target chip are determined through the flow compensation margin, that is: select an argon gas flow domain, subtract the upper bound of the argon gas flow in this argon gas flow domain from the flow compensation margin, and use the subtracted value as the flow compensation value of the pin of the target chip corresponding to this argon gas flow domain, and continue to determine the flow compensation values of the pins of the target chip corresponding to the remaining argon gas flow domains.

[0127] It should be noted that the flow compensation value in this application represents the parameter value for compensating the argon gas flow on the chip pins. By adjusting the flow compensation value, it can be ensured that the solder is evenly distributed during the welding process of the chip pins, avoiding the situation of too much or too little solder.

[0128] In step 106, according to all the flow compensation values and the torch offset, the variable solder amounts at different positions of the target chip pins are determined, and each pin of the target chip is heated and welded through all the variable solder amounts.

[0129] In some embodiments, refer to Figure 3 As shown, this figure is a schematic flow chart for determining the variable solder amount in some embodiments of this application. In this embodiment, the variable solder amounts at different positions of the target chip pins are determined according to all the flow compensation values and the torch offset, which can be implemented by the following steps:

[0130] First, in step 1061, the solder adjustment coefficients at different positions of the target chip pins are determined according to all the flow compensation values and the torch offset;

[0131] Secondly, in step 1062, the variable solder amounts at different positions of the target chip pins are determined through all the solder adjustment coefficients and the preset solder equalization amount.

[0132] In specific implementation, the solder adjustment coefficients at different positions of the target chip pins are determined according to all the flow compensation values and the torch offset, that is: select a flow compensation value, divide this flow compensation value by the torch offset, and use the divided value as the solder adjustment coefficient of the chip pin corresponding to this flow compensation value, and continue to determine the solder adjustment coefficients of the chip pins corresponding to the remaining flow compensation values.

[0133] It should be noted that the solder adjustment coefficient in this application represents the parameter for adjusting the solder amount and distribution at different positions of the target chip pins.

[0134] In specific implementation, the variable solder amount at different positions of the target chip pins is determined by all the solder adjustment coefficients and the preset solder equalization amount, that is: select a solder adjustment coefficient. If the solder adjustment coefficient is greater than 0, the value obtained by adding the solder adjustment coefficient and the solder equalization amount is used as the variable solder amount of the chip pin corresponding to this solder adjustment coefficient. If the solder adjustment coefficient is less than or equal to 0, the value obtained by subtracting the solder equalization amount from the solder adjustment coefficient is used as the variable solder amount of the chip pin corresponding to this solder adjustment coefficient, and then continue to determine the variable solder amounts of the chip pins corresponding to the remaining solder adjustment coefficients.

[0135] It should be noted that in this application, the variable solder amount represents the solder amount required at different positions of the target chip pins.

[0136] In some embodiments, heating and soldering each pin of the target chip with all the variable solder amounts can be implemented by the following steps:

[0137] Obtain the distribution vector of the solder joints to be welded;

[0138] Perform pulsed heating soldering on each pin of the target chip according to the distribution vector of the solder joints to be welded and all the variable solder amounts.

[0139] In specific implementation, performing pulsed heating soldering on each pin of the target chip according to the distribution vector of the solder joints to be welded and all the variable solder amounts, that is: select a solder joint component from the distribution vector of the solder joints to be welded, and use a pulsed heating device (such as a resistance heater, an induction heater, a microwave heater, etc.) to perform periodic pulsed heating on the solder until the solder amount reaches the variable solder amount of the chip pin corresponding to this solder joint component, then stop heating, and then use a soldering gun to align the heated solder amount with the position coordinates of the solder joint of the chip pin corresponding to this solder joint component, and finally release the heated solder amount to the solder joint of the chip pin, and continue to perform pulsed heating soldering on the solder joints of the chip pins corresponding to the remaining solder joint components in the distribution vector of the solder joints to be welded.

[0140] It should be noted that the solder in this application can use welding materials such as solder, solder paste, and solder adhesive.

[0141] In addition, on the other hand of this application, in some embodiments, this application provides a chip soldering system. Refer to Figure 4 , this figure is a schematic diagram of the exemplary hardware and / or software of the chip soldering system according to some embodiments of this application. The chip soldering system 400 includes: an acquisition module 401, a processing module 402, and an execution module 403, which are described as follows:

[0142] An acquisition module 401, in this application, the acquisition module 401 is mainly used to obtain a welding pressure data set during the historical chip welding after starting chip welding;

[0143] A processing module 402, in this application, the processing module 402 is used to divide the welding pressure data into multiple discrete pressure data segments through the discrete features of the welding pressure data set, and determine the pressure deviation coefficient of the target chip according to all the discrete pressure data segments;

[0144] It should be noted that in this application, the processing module 402 is also used to obtain a pre-welding image of the target chip, and extract the distribution vector of the solder joints to be welded of the target chip pins from the pre-welding image based on a pre-trained solder joint feature model;

[0145] It should be noted that in this application, the processing module 402 is also used to determine the torch offset amount during the welding of the target chip through the pressure deviation coefficient and the distribution vector of the solder joints to be welded;

[0146] In addition, in this application, the processing module 402 is also used to determine the argon gas flow domains of the solder joints to be welded of each pin of the target chip based on the argon gas flow data set during the historical chip welding and the distribution vector of the solder joints to be welded, and then determine the flow compensation values of each pin of the target chip according to all the argon gas flow domains;

[0147] An execution module 403, in this application, the execution module 403 is mainly used to determine the variable solder amounts at different positions of the target chip pins according to all the flow compensation values and the torch offset amount, and heat and weld each pin of the target chip through all the variable solder amounts.

[0148] In addition, this application also provides a computer device, the computer device includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the above chip welding method.

[0149] In some embodiments, refer to Figure 5 , this figure is a schematic structural diagram of a computer device applying the chip welding method according to some embodiments of this application. The chip welding method in the above embodiments can be implemented by Figure 5 The computer device shown, the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0150] The processor 501 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the method for chip soldering in this application.

[0151] The communication bus 502 may include a path for transmitting information between the above components.

[0152] The memory 503 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or it can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but not limited to this. The memory 503 can exist independently and be connected to the processor 501 through the communication bus 502. The memory 503 can also be integrated with the processor 501.

[0153] Among them, the memory 503 is used to store the program code for executing the solution of this application and is controlled by the processor 501 to execute. The processor 501 is used to execute the program code stored in the memory 503. The program code can include one or more software modules. The determination of the solder joint distribution vector in the above embodiments can be implemented by one or more software modules in the program code in the processor 501 and the memory 503.

[0154] The communication interface 504, using any device such as a transceiver, is used to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0155] In a specific implementation, as an example, a computer device may include multiple processors, and each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0156] The above computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0157] In addition, the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above method for chip soldering is implemented.

[0158] In summary, in the method, system, and storage device for chip soldering disclosed in the embodiments of the present application, chip soldering is started, a welding pressure data set during historical chip soldering is obtained, the welding pressure data is divided into multiple discrete pressure data segments through the discrete features of the welding pressure data set, a pressure deviation coefficient of the target chip is determined according to all the discrete pressure data segments, a pre-soldering image of the target chip is obtained, a distribution vector of solder joints to be soldered of the pins of the target chip is extracted from the pre-soldering image based on a pre-trained solder joint feature model, a torch offset amount during soldering of the target chip is determined through the pressure deviation coefficient and the distribution vector of solder joints to be soldered, an argon gas flow domain of each solder joint to be soldered of the pins of the target chip is determined based on the argon gas flow data set during historical chip soldering and the distribution vector of solder joints to be soldered, and then a flow compensation value of each pin of the target chip is determined according to all the argon gas flow domains, so that a variable solder amount at different positions of the pins of the target chip is determined according to all the flow compensation values and the torch offset amount, and each pin of the target chip is heated and soldered through all the variable solder amounts, thereby realizing dynamic adjustment of the solder amount during the chip soldering process.

[0159] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0160] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these modifications and variations.

Claims

1. A chip welding method, characterized in that: The steps include: Start chip welding and obtain the welding pressure data set when welding the chip in history; Dividing the welding pressure data into a plurality of discrete pressure data segments according to the discrete characteristics of the welding pressure data set, and determining the pressure deviation coefficient of the target chip according to all the discrete pressure data segments; Acquire a pre-welding image of a target chip, and extract a distribution vector of solder joints to be soldered of the pins of the target chip from the pre-welding image based on a pre-trained solder joint feature model; Determine the welding gun offset when welding the target chip by using the pressure deviation coefficient and the distribution vector of the points to be welded; Based on the argon flow data set when welding chips in history and the distribution vector of the points to be welded, the argon flow domain of each point to be welded of the pin of the target chip is determined, and then the flow compensation value of each pin of the target chip is determined according to all the argon flow domains, so as to determine the variable solder amount of the pin of the target chip at different positions according to all the flow compensation values ​​and the welding gun offset, and the pins of the target chip are heated and welded by all the variable solder amounts; Among them, the argon flow rate domain represents the range consisting of the lower limit of the argon flow rate and the upper limit of the argon flow rate during the chip welding process, wherein the lower limit of the argon flow rate represents the minimum allowable value of the argon flow rate on the chip pin during the welding process, and the upper limit of the argon flow rate represents the maximum allowable value of the argon flow rate on the chip pin during the welding process.

2. The method according to claim 1, characterized in that Dividing the welding pressure data into a plurality of discrete pressure data segments according to the discrete features of the welding pressure data set specifically includes: determining a plurality of welding pressure change rate sequences according to the welding pressure data set; Determining discrete features of the welding pressure data set through all welding pressure change rate sequences; Determining a feature partition coefficient of the welding pressure data set according to the discrete feature; The welding pressure data set is divided into a plurality of discrete pressure data segments by the characteristic division coefficient.

3. The method according to claim 1, characterized in that Determining the pressure deviation coefficient of the target chip based on all discrete pressure data segments specifically includes: Determine the pressure extreme value difference of each discrete pressure data segment; Determining a welding pressure equilibrium value of a target chip according to the welding pressure data set; The pressure deviation coefficient of the target chip is determined by all the pressure extreme value differences and the welding pressure equilibrium value.

4. The method according to claim 1, characterized in that Extracting the distribution vector of the solder joints of the target chip pins from the pre-soldering image based on the pre-trained solder joint feature model specifically includes: Acquire a historical pre-welding image set of chips of the same type as the target chip; Training a feature model of the spot to be welded based on the historical pre-welding image set; The feature model of the points to be soldered is used to extract features from the pre-soldering image of the target chip to obtain a distribution vector of the points to be soldered of the pins of the target chip.

5. The method according to claim 1, characterized in that Determining the argon flow domain of each to-be-welded point of the target chip pin based on the argon flow data set during the chip welding history and the distribution vector of the to-be-welded points specifically includes: Obtain the argon gas flow data set during chip welding in history; extracting an argon flow sequence from the argon flow data set; Selecting a first argon gas flow rate from the argon gas flow rate sequence; Determine the upper limit and the lower limit of the argon gas flow rate of the target chip pin to be welded corresponding to the argon gas flow rate through the distribution vector of the to-be-welded points; The range formed by the upper limit of the argon gas flow rate and the lower limit of the argon gas flow rate is used as the argon gas flow rate domain of the target chip pin to be welded corresponding to the argon gas flow rate; Continue to determine the argon gas flow rate domain of the target chip pin's to-be-welded point corresponding to the remaining argon gas flow rate in the argon gas flow rate sequence.

6. The method according to claim 1, characterized in that Determining the flow compensation value of each pin of the target chip based on all argon gas flow domains specifically includes: Determine the flow compensation margin of the target chip according to all argon gas flow domains; The flow compensation value of each pin of the target chip is determined by the flow compensation margin.

7. The method according to claim 1, characterized in that Determining the variable solder amount at different positions of the target chip pin according to all flow compensation values ​​and the welding gun offset specifically includes: Determine the solder adjustment coefficient of the target chip pin at different positions according to all flow compensation values ​​and the welding gun offset; The variable solder amounts of the target chip pins at different positions are determined by all solder adjustment coefficients and the preset solder balance amount.

8. A chip bonding system, which uses the method according to any one of claims 1 to 7 to perform chip bonding, characterized in that: The system includes: An acquisition module is used to acquire a welding pressure data set during chip welding in history after chip welding is started; A processing module, used to divide the welding pressure data into a plurality of discrete pressure data segments according to the discrete features of the welding pressure data set, and determine the pressure deviation coefficient of the target chip according to all the discrete pressure data segments; The processing module is further used to obtain a pre-welding image of the target chip, and extract a distribution vector of the to-be-welded points of the pins of the target chip from the pre-welding image based on a pre-trained solder point feature model; The processing module is further used to determine the welding gun offset when welding the target chip through the pressure deviation coefficient and the distribution vector of the points to be welded; The processing module is further used to determine the argon flow domain of each to-be-welded point of the target chip pin based on the argon flow data set when welding the chip in the history and the distribution vector of the to-be-welded point, and then determine the flow compensation value of each pin of the target chip according to all the argon flow domains; The execution module is used to determine the variable solder amounts of the pins of the target chip at different positions according to all the flow compensation values ​​and the welding gun offset, and to heat and weld each pin of the target chip using all the variable solder amounts.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the chip bonding method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the chip bonding method according to any one of claims 1 to 7 are implemented.

Images