Adaptive optimization method of reflow process parameters
By collecting solder parameters and dot images, combining preheating and constant temperature parameters to predict impurity elimination and reflow flattening prediction, optimizing the reflow soldering process parameters, solving the problem of difficult to ensure the consistency and stability of welding quality in the existing technology, and realizing the Higher adaptability and welding quality.
Patent Information
- Application Number
- CN202410885439.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-03
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-07-03
AI Technical Summary
The existing reflow soldering process parameter setting methods rely on fixed specifications and empirical adjustments, and lack adaptive adjustments to real-time process conditions and solder characteristics, making it difficult to guarantee the consistency and stability of solder quality.
By collecting solder parameters and dot image, identifying dot specification information, combining preheating parameters and constant temperature parameters for impurity elimination prediction, optimizing preheating and constant temperature parameters, combining optimal impurity elimination parameters for solder reflow flattening prediction, and optimizing reflow parameters for reflow parameters. , generate an adaptively optimized reflow soldering process.
It improves the adaptability and flexibility of process parameters, and improves the consistency and stability of welding quality.
Smart Images

Figure CN118428244B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to data processing related fields, and in particular to a method for adaptively optimizing reflow soldering process parameters. Background Art
[0002] With the rapid development of the electronics manufacturing industry, the reflow soldering process is a key step in the assembly process of electronic components, and its welding quality directly affects the reliability and performance of the product. The existing reflow soldering process parameter setting method is mainly based on parameter setting based on fixed process specifications and adjustment based on experience parameters. However, the adjustment method based on experience parameters is overly dependent on the skills and experience of the operator, and is easily affected by human factors. It lacks adaptive adjustment to real-time process conditions and solder characteristics. This static parameter setting method is often difficult to ensure the consistency and stability of soldering quality when facing complex production environments and changeable solder characteristics.
[0003] In the current related technologies, there is a technical problem that the adjustment of reflow soldering process parameters lacks adaptability and it is difficult to ensure the reliability and consistency of welding quality. Summary of the invention
[0004] The present application provides a method for adaptively optimizing reflow soldering process parameters, collects solder parameters and spot material images, identifies spot material specification information, predicts solder impurity elimination in combination with preheating parameters and constant temperature parameters, calculates impurity elimination parameter deviations, optimizes preheating parameters and constant temperature parameters, predicts solder reflow paving in combination with optimal impurity elimination parameters, optimizes reflow parameters and other technical means, thereby achieving the technical effect of improving the adaptability and flexibility of process parameters and improving the consistency and stability of welding quality through adaptive optimization of process parameters.
[0005] The present application provides a method for adaptively optimizing reflow soldering process parameters, including:
[0006] Collect solder parameters for reflow soldering, collect solder spotting images after solder spotting, identify and obtain spotting specification information; collect preheating parameters and constant temperature parameters in the current reflow soldering process, combine the solder parameters and spotting specification information to predict solder impurity elimination, and obtain solder impurity elimination parameters; when the solder impurity elimination parameters do not meet the requirements of the preset threshold impurity elimination parameters, calculate the impurity elimination parameter deviation, set the preparation optimization step size, optimize the preheating parameters and constant temperature parameters, obtain the optimal preheating parameters and the optimal constant temperature parameters, and obtain the optimal impurity elimination parameters. number; collect the reflow parameters in the current reflow soldering process, combine with the optimal impurity elimination parameters, perform solder reflow leveling prediction, and obtain reflow leveling parameters; when the reflow leveling parameters do not meet the requirements of the preset threshold reflow leveling parameters, calculate the reflow leveling parameter deviation, set the reflow optimization step, optimize the reflow parameters, and obtain the optimal reflow parameters, wherein, during the optimization process, the reflow leveling parameters are predicted based on the optimal impurity elimination parameters and the reflow parameters; based on the optimal preheating parameters, the optimal constant temperature parameters and the optimal reflow parameters, an optimized reflow soldering process is generated.
[0007] In a possible implementation, solder parameters for reflow soldering are collected, and a solder point image after solder point is collected, and the solder point specification information is identified and obtained, and the following processing is performed:
[0008] The solder components of the reflow soldering are detected to obtain solder parameters, wherein the solder components include alloy, flux, and solvent; the dotted material images after solder dotting on the target circuit board are collected; according to the data records of the circuit board reflow soldering, a set of sample dotted material images are collected, and the dotted material specifications are marked to obtain a set of sample dotted material specification information, and a dotted material specification identifier is trained; the dotted material image is identified using the dotted material specification identifier to obtain the dotted material specification information.
[0009] In a possible implementation, the preheating parameters and constant temperature parameters in the current reflow process are collected, and the solder impurity elimination prediction is performed in combination with the solder parameters and the spot material specification information, and the following processing is performed:
[0010] Collect a sample solder parameter set, a sample material point specification information set, a sample preheating parameter set and a sample constant temperature parameter set, and collect a sample solder impurity elimination parameter set based on the preheating and constant temperature stage data under different preheating parameters, constant temperature parameters, solder parameters and material point specification information; use the sample solder parameter set, the sample material point specification information set, the sample preheating parameter set and the sample constant temperature parameter set as input, use the sample solder impurity elimination parameter set as output, train an impurity elimination predictor, perform solder impurity elimination prediction on the preheating parameters, constant temperature parameters, solder parameters and material point specification information, and obtain solder impurity elimination parameters.
[0011] In a possible implementation, when the solder impurity elimination parameter does not meet the requirement of the preset threshold impurity elimination parameter, the impurity elimination parameter deviation is calculated, the preparation optimization step is set, the preheating parameter and the constant temperature parameter are optimized, and the following processing is performed:
[0012] Determine whether the solder impurity elimination parameter meets the requirement of the threshold impurity elimination parameter. If yes, do not optimize the preheating parameter and the constant temperature parameter. If not, calculate and obtain the impurity elimination parameter deviation. According to the impurity elimination parameter deviation, correct the preset step length to obtain the preparation optimization step length. Construct a preparation optimization function for optimizing the preheating parameter and the constant temperature parameter, as shown in the following formula: ; Among them, PF is the preparation fitness, To optimize the impurity elimination parameters after preheating parameters and constant temperature parameters, is a threshold impurity elimination parameter; the preparation optimization step is used to adjust the preheating parameter and the constant temperature parameter to obtain a first preheating parameter and a first constant temperature parameter; the first preheating parameter and the first constant temperature parameter are used, combined with the solder parameter and the point material specification information, to predict the solder impurity elimination to obtain the first impurity elimination parameter, and the first preparation fitness is calculated; it is determined whether the first impurity elimination parameter is greater than the solder impurity elimination parameter, if so, the preparation optimization step is reduced, if not, the preparation optimization step is enlarged, the first preheating parameter and the first constant temperature parameter are adjusted to obtain a second preheating parameter and a second constant temperature parameter, and the second impurity elimination parameter and the second preparation fitness are predicted and processed; the second preparation fitness and the first preparation fitness are judged to obtain an optimization basis; the optimization and update are continued based on the optimization basis until convergence, and the final optimal preheating parameter and the optimal constant temperature parameter are output.
[0013] In a possible implementation, a judgment is made according to the second preparation fitness and the first preparation fitness to obtain an optimization basis, and the following processing is performed:
[0014] When the second preparation fitness is greater than the first preparation fitness, the second preheating parameter and the second constant temperature parameter are used as optimization basis; when the second preparation fitness is not greater than the first preparation fitness, the proximity of the second impurity elimination parameter and the first impurity elimination parameter is calculated, and when the proximity is greater than a preset proximity threshold, the second preheating parameter and the second constant temperature parameter are used as optimization basis, otherwise, the first preheating parameter and the first constant temperature parameter are used as optimization basis.
[0015] In a possible implementation, the reflow parameters in the current reflow soldering process are collected, combined with the optimal impurity elimination parameters, solder reflow leveling prediction is performed, the reflow leveling parameters are obtained, and the following processing is performed:
[0016] According to the processing data records of the reflow stage of reflow soldering, a sample reflow parameter set, a sample impurity elimination parameter set, and a sample reflow leveling parameter set are collected, wherein the sample reflow leveling parameters include the leveling uniformity parameters of the solder joints after reflow; the sample reflow parameter set, the sample impurity elimination parameter set, and the sample reflow leveling parameter set are used to train a reflow leveling predictor, and the solder reflow leveling prediction is performed on the reflow parameters and the optimal impurity elimination parameters to obtain the reflow leveling parameters.
[0017] In a possible implementation, when the reflow paving parameter does not meet the requirement of the preset threshold reflow paving parameter, the reflow paving parameter deviation is calculated, the reflow optimization step is set, the reflow parameter is optimized, the optimal reflow parameter is obtained, and the following processing is performed:
[0018] Determine whether the reflow paving parameters meet the requirements of the threshold reflow paving parameters. If yes, do not optimize the reflow parameters. If not, calculate and obtain the reflow paving parameter deviation. According to the reflow paving parameter deviation, correct the preset step size to obtain the reflow optimization step size. Construct a reflow optimization function for optimizing the reflow parameters, as shown in the following formula: ; Among them, HF is the reflux fitness, To optimize the reflow parameters after reflow paving, Paving parameters for threshold reflow; optimizing the reflow parameters according to the reflow optimization step size and the reflow optimization function to obtain optimal reflow parameters.
[0019] In a possible implementation, the reflow parameters are optimized according to the reflow optimization step size and the reflow optimization function, and the following processing is performed:
[0020] The reflux optimization step is used to adjust the reflux parameters to obtain the first reflux parameters; the first reflux parameters are used in combination with the optimal impurity elimination parameters to perform reflux paving prediction to obtain the first reflux paving parameters, and the first reflux fitness is calculated; it is determined whether the first reflux paving parameter is greater than the reflux paving parameter, if so, the reflux optimization step is reduced, if not, the reflux optimization step is enlarged, the first reflux parameter is adjusted to obtain the second reflux parameter, and the second reflux paving parameter and the second reflux fitness are obtained by prediction and processing; the second reflux fitness and the first reflux fitness are judged to obtain the optimization basis, and the optimization is performed until convergence, and the final optimal reflux parameters are output.
[0021] The method for adaptive optimization of reflow soldering process parameters proposed in the present application first collects solder parameters for reflow soldering, and collects solder spotting images after solder spotting, identifies and obtains spotting specification information, then collects preheating parameters and constant temperature parameters in the current reflow soldering process, combines the solder parameters and spotting specification information, predicts solder impurity elimination, obtains solder impurity elimination parameters, and then, when the solder impurity elimination parameters do not meet the requirements of the preset threshold impurity elimination parameters, calculates the impurity elimination parameter deviation, sets the preparation optimization step size, optimizes the preheating parameters and constant temperature parameters, obtains the optimal preheating parameters and the optimal constant temperature parameters, and obtains the optimal impurity elimination parameters, and then collects the current reflow soldering process. The reflow parameters in the process are combined with the optimal impurity elimination parameters to predict the solder reflow leveling and obtain the reflow leveling parameters. Then, when the reflow leveling parameters do not meet the requirements of the preset threshold reflow leveling parameters, the reflow leveling parameter deviation is calculated, the reflow optimization step is set, the reflow parameters are optimized, and the optimal reflow parameters are obtained. In the optimization process, the reflow leveling parameters are predicted based on the optimal impurity elimination parameters and the reflow parameters. Finally, the optimized reflow soldering process is generated based on the optimal preheating parameters, the optimal constant temperature parameters and the optimal reflow parameters, thereby achieving the technical effect of improving the adaptability and flexibility of the process parameters and improving the consistency and stability of the welding quality by adaptively optimizing the process parameters. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] 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.
[0023] Figure 1 A schematic flow chart of a method for adaptively optimizing reflow soldering process parameters provided in an embodiment of the present application.
[0024] Figure 2 A schematic diagram of the process of optimizing preheating parameters and constant temperature parameters in the method for adaptively optimizing reflow soldering process parameters provided in an embodiment of the present application. DETAILED DESCRIPTION
[0025] 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.
[0026] In order to make the purpose, 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.
[0027] 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 thereof 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 that are 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.
[0028] The present application embodiment provides a method for adaptively optimizing reflow process parameters, such as Figure 1 As shown, the method includes:
[0029] Step S100, collect solder parameters for reflow soldering, and collect solder spotting images after solder spotting, and identify and obtain spotting specification information. Specifically, use sensors, analytical instruments and other equipment to measure the physical and chemical parameters of solder (materials used to weld two or more metals or metal and non-metal surfaces), including but not limited to the melting point, component ratio (such as alloy components such as tin, silver, copper, etc.), particle size, viscosity, thermal conductivity, etc. of the solder. After solder spotting, use high-definition cameras, microscopes and other equipment to capture images of the spotting area, that is, images of the actual distribution of solder spots on the PCB (printed circuit board), and use image processing software to process the spotting images, including steps such as denoising, contrast enhancement, and edge detection, to improve image quality and highlight the features of the spotting materials, and extract the feature information of the spotting materials from the processed images, such as the shape, size, quantity, spacing, etc. of the spotting materials, and use machine learning or deep learning algorithms based on the extracted feature information to identify the spotting material specifications, including detailed information such as the type, size range, and distribution of the spotting materials.
[0030] In a possible implementation, step S100 further includes step S110, detecting the solder components for reflow soldering to obtain solder parameters, wherein the solder components include alloys, flux, and solvents. Specifically, a representative sample is selected from the solder to be soldered, and the key parameters such as the alloy components (the main metal components in the solder, such as tin, lead, silver, etc.), flux (a substance that helps remove oxides, reduce surface tension, and promote metal diffusion during the soldering process) type and content, and solvent (a part of the flux, used to dissolve other components in the flux and volatilize during the soldering process) type and content in the solder sample are detected by using methods such as chemical analysis or spectral analysis, and the detected solder parameters are recorded in detail, such as the alloy ratio, the type and content of flux and solvent, etc. Step S120, collecting the dotted image after solder dotting on the target circuit board. Specifically, the circuit board to be soldered (substrate for mounting electronic components) is placed in a suitable position, a spotting machine or other equipment is used to spot solder at a designated position of the target circuit board, and a high-resolution camera or camera is used to capture the solder spotting image on the circuit board. Step S130, according to the data record of the circuit board reflow, a sample spotting image set is collected, and the spotting specifications are marked, a sample spotting specification information set is obtained, and a spotting specification identifier is trained. Specifically, from the data record of the circuit board reflow, spotting images of different spotting specifications are selected to form a sample spotting image set, and each image in the sample spotting image set is annotated with spotting specifications (characteristic parameters such as the shape, size, and position of the solder point on the circuit board) to form a sample spotting specification information set. A machine learning algorithm suitable for image recognition is selected, such as a convolutional neural network (CNN), and a spotting specification identifier is trained using a sample spotting image set and a corresponding sample spotting specification information set, and the spotting specification identifier can automatically identify and classify the spotting specifications on the circuit board. Step S140, using the point material specification identifier, the point material image is identified to obtain the point material specification information. Specifically, the point material image collected in step S120 is input into the point material specification identifier, and the point material specification identifier processes and analyzes the input image to identify the specification information of the point material. This implementation method realizes automatic recognition of point material specifications by training the point material specification identifier, reduces manual operations and errors, and achieves the technical effect of improving the accuracy and efficiency of recognition.
[0031] Step S200, collect the preheating parameters and constant temperature parameters in the current reflow process, combine the solder parameters and the material specification information, predict the solder impurity elimination, and obtain the solder impurity elimination parameters. Specifically, use a sensor or equipment control system to collect the preheating parameters (temperature, time and other parameters used to heat the solder before reflow, such as preheating temperature, preheating time, etc.) and constant temperature parameters (parameters for keeping the solder temperature stable after preheating, such as constant temperature, constant temperature time, etc.) data in the current reflow process in real time. Based on historical data and experience, select or train a suitable model or algorithm to predict the degree of impurity elimination in the solder, which can be a model based on physical principles or a model trained by machine learning or deep learning. The currently collected preheating parameters and constant temperature parameters, as well as solder parameters and point material specification information are used as input and input into the model or algorithm. The model or algorithm is run to calculate the degree of elimination of impurities (unnecessary substances mixed into the solder during the welding process, such as solvents, oxides, metal particles, etc.) in the solder during the preheating and constant temperature process based on the input parameters, including the prediction of the volatilization amount of solvent in the solder, the residual amount of impurities, etc. The output of the model or algorithm is the solder impurity elimination parameter (parameter for predicting the degree of impurity elimination in the solder), such as the impurity elimination rate, etc.
[0032] In a possible implementation, step S200 further includes step S210, collecting a sample solder parameter set, a sample spot material specification information set, a sample preheating parameter set and a sample constant temperature parameter set, and collecting a sample solder impurity elimination parameter set according to the preheating and constant temperature stage data under different preheating parameters, constant temperature parameters, solder parameters and spot material specification information. Specifically, historical welding data is collected, including solder parameters (such as alloy composition, flux type, etc.), spot material specification information (such as spot material size, shape, etc.), preheating parameters (such as preheating temperature, time, etc.) and constant temperature parameters (such as constant temperature, time, etc.) of different batches, and data related to the solder impurity elimination recorded in the preheating and constant temperature stages according to different preheating parameters, constant temperature parameters, solder parameters and spot material specification information, such as impurity type, quantity, distribution, etc., which constitute a sample solder impurity elimination parameter set. The collected data is classified and sorted according to different parameter combinations to form a one-to-one corresponding sample data set. Step S220, using the sample solder parameter set, sample material point specification information set, sample preheating parameter set and sample constant temperature parameter set as input, using the sample solder impurity elimination parameter set as output, training the impurity elimination predictor, performing solder impurity elimination prediction on the preheating parameters, constant temperature parameters, solder parameters and material point specification information, and obtaining solder impurity elimination parameters. Specifically, according to the characteristics of the problem, a suitable machine learning or deep learning algorithm is selected, such as support vector machine (SVM), random forest or neural network, etc., and necessary preprocessing is performed on the sample data collected in step S210, such as data cleaning, normalization, encoding, etc., using the preprocessed sample data as input, and the corresponding sample solder impurity elimination parameters as output, to train the impurity elimination predictor, which can predict the solder impurity elimination situation according to the given preheating parameters, constant temperature parameters, solder parameters and material point specification information, and output the solder impurity elimination parameters. This implementation method realizes the automatic prediction of solder impurity elimination parameters by establishing a prediction model, and achieves the technical effect of improving the accuracy and efficiency of solder impurity elimination prediction.
[0033] Step S300, when the solder impurity elimination parameter does not meet the requirements of the preset threshold impurity elimination parameter, calculate the impurity elimination parameter deviation, set the preparation optimization step, optimize the preheating parameter and the constant temperature parameter, obtain the optimal preheating parameter and the optimal constant temperature parameter, and obtain the optimal impurity elimination parameter. Specifically, according to the process requirements and quality standards, a threshold impurity elimination parameter is pre-set as a benchmark for judging whether the current impurity elimination effect meets the standard. The obtained solder impurity elimination parameter is compared with the preset threshold impurity elimination parameter. If the current solder impurity elimination parameter is lower than the threshold value, the deviation between the current solder impurity elimination parameter and the threshold value is calculated. The deviation can be an absolute value, a percentage or other appropriate measurement method. According to the characteristics of the problem and the actual situation, select a suitable optimization algorithm, such as gradient descent method, genetic algorithm, particle swarm optimization algorithm, etc., and set a suitable preparation optimization step according to the requirements of the optimization algorithm and the sensitivity of the problem. The optimization process starts with the current preheating parameters and constant temperature parameters as initial values. The preheating parameters and constant temperature parameters are iteratively adjusted according to the optimization algorithm and the set preparation optimization step size. In each iteration, the solder impurity elimination parameters are recalculated according to the adjusted parameters, and it is evaluated whether they meet the requirements. During the optimization process, if a certain set of parameters is found to produce a better impurity elimination effect (that is, the solder impurity elimination parameters are higher), then this set of parameters is recorded as the current optimal parameters. When certain ending conditions are met (such as reaching the preset number of iterations, the optimization effect of multiple consecutive iterations is not obvious, etc.), the optimization process is stopped, and the final optimal preheating parameters, optimal constant temperature parameters and corresponding optimal impurity elimination parameters are output.
[0034] like Figure 2As shown, in a possible implementation, when the solder impurity elimination parameter does not meet the requirements of the preset threshold impurity elimination parameter, the impurity elimination parameter deviation is calculated, the preparation optimization step is set, and the preheating parameter and the constant temperature parameter are optimized. Step S300 further includes step S310, judging whether the solder impurity elimination parameter meets the requirements of the threshold impurity elimination parameter. If so, the preheating parameter and the constant temperature parameter are not optimized. If not, the impurity elimination parameter deviation is calculated. Specifically, the current solder impurity elimination parameter is compared with the preset threshold impurity elimination parameter (the preset standard value or the lowest acceptable value of the solder impurity elimination parameter). If the current solder impurity elimination parameter meets or exceeds the threshold value, the preheating parameter and the constant temperature parameter are not optimized; if not, the next step is entered to calculate the deviation value between the current solder impurity elimination parameter and the threshold impurity elimination parameter. Step S320, according to the impurity elimination parameter deviation, the preset step is corrected to obtain the preparation optimization step. Specifically, based on the impurity elimination parameter deviation and other factors (such as historical data, system stability, etc.), the preset step size is corrected to obtain the preparation optimization step size, which is the step size used for subsequent adjustment of the preheating parameters and the constant temperature parameters. Step S330, construct a preparation optimization function for optimizing the preheating parameters and the constant temperature parameters, as shown in the following formula: ; Among them, PF is the preparation fitness, To optimize the impurity elimination parameters after preheating parameters and constant temperature parameters, is the threshold impurity elimination parameter. Specifically, the preparation optimization function is a mathematical function used to guide the optimization process of the preheating parameters and the constant temperature parameters, and the preparation fitness is an indicator for evaluating the effect of solder impurity elimination under the optimized preheating parameters and the constant temperature parameters. Step S340, using the preparation optimization step length, the preheating parameters and the constant temperature parameters are adjusted to obtain the first preheating parameters and the first constant temperature parameters. Specifically, the preheating parameters and the constant temperature parameters are adjusted using the preparation optimization step length, and the adjusted parameters are the first preheating parameters and the first constant temperature parameters. Step S350, using the first preheating parameters and the first constant temperature parameters, combined with the solder parameters and the point material specification information, solder impurity elimination prediction is performed to obtain the first impurity elimination parameter, and the first preparation fitness is calculated. Specifically, using the first preheating parameters and the first constant temperature parameters, combined with the solder parameters and the point material specification information, the new impurity elimination parameters are predicted by the impurity elimination predictor, and the first preparation fitness is calculated by the preparation optimization function according to the prediction results and the threshold impurity elimination parameters. Step S360, determine whether the first impurity elimination parameter is greater than the solder impurity elimination parameter, if so, reduce the preparation optimization step length, if not, enlarge the preparation optimization step length, adjust the first preheating parameter and the first constant temperature parameter, obtain the second preheating parameter and the second constant temperature parameter, and predict and process to obtain the second impurity elimination parameter and the second preparation fitness. Specifically, compare the first impurity elimination parameter with the solder impurity elimination parameter. If the first impurity elimination parameter is better, it is necessary to reduce the preparation optimization step length; if it is not as good as the current value, it is necessary to enlarge the preparation optimization step length. After adjusting the preparation optimization step length, adjust the preheating parameter and the constant temperature parameter again to obtain the second preheating parameter and the second constant temperature parameter, and predict and obtain the second impurity elimination parameter and the second preparation fitness. Step S370, judge according to the second preparation fitness and the first preparation fitness to obtain the optimization basis. Specifically, compare the first preparation fitness and the second preparation fitness, and determine the direction and strategy of subsequent optimization based on the comparison result of the preparation fitness. Step S380, continue to optimize and update based on the optimization basis until convergence, and output the final optimal preheating parameter and the optimal constant temperature parameter. Specifically, based on the optimization foundation, the preheating parameters and constant temperature parameters are continuously optimized and updated until the convergence conditions are met (such as the fitness improvement is no longer obvious or the preset maximum number of iterations is reached), and the final optimal preheating parameters and optimal constant temperature parameters are output. This implementation method gradually approaches the optimal combination of preheating parameters and constant temperature parameters through precise prediction and iterative optimization, achieving the technical effect of achieving accurate and efficient optimization.
[0035] In a possible implementation, step S370 further includes step S371, when the second preparation fitness is greater than the first preparation fitness, the second preheating parameters and the second constant temperature parameters are used as the optimization basis. Specifically, the second preparation fitness is compared with the first preparation fitness. If the second preparation fitness is greater than the first preparation fitness, it means that the effect of the second set of parameters is better, so the second preheating parameters and the second constant temperature parameters are used as the basis for subsequent optimization. Step S372, when the second preparation fitness is not greater than the first preparation fitness, the proximity of the second impurity elimination parameter and the first impurity elimination parameter is calculated. When the proximity is greater than a preset proximity threshold, the second preheating parameters and the second constant temperature parameters are used as the optimization basis, otherwise, the first preheating parameters and the first constant temperature parameters are used as the optimization basis. Specifically, if the second preparation fitness is not greater than the first preparation fitness, the proximity of the two impurity elimination parameters is further calculated. The proximity refers to the similarity or closeness between the two impurity elimination parameters. The difference or other similarity measurement methods can be used to calculate. If the proximity is greater than the preset proximity threshold, it means that the two impurity elimination parameters are very close. In order to avoid the instability caused by frequent parameter switching, the second set of parameters is still selected as the optimization basis; if the proximity is not greater than the preset proximity threshold, the first set of parameters is selected as the optimization basis, because the second set of parameters does not significantly improve the impurity elimination effect, and the difference is large. This implementation method allows a certain degree of flexibility in the parameter selection process by presetting the proximity threshold. Even if the preparation fitness of the second set of parameters is slightly lower, if the two sets of parameters are very close, the second set of parameters can still be selected as the optimization basis to explore more possibilities, thereby achieving the technical effect of improving the flexibility of the optimization process.
[0036] Step S400, collect the reflow parameters in the current reflow soldering process, combine the optimal impurity elimination parameters, perform solder reflow flattening prediction, and obtain the reflow flattening parameters. Specifically, use a sensor or equipment control system to collect the reflow parameter (reflow temperature, reflow time, reflow speed, etc.) data in the current reflow soldering process in real time. According to historical data and experience, select a suitable model or algorithm to predict the flattening effect of the solder during the reflow process, which can be a model based on physical principles or a model trained by machine learning or deep learning. The currently collected reflow parameters, optimal impurity elimination parameters, solder parameters and point material specification information are used as inputs, input into the model or algorithm, run the model or algorithm, and calculate the flattening effect of the solder during the reflow process based on the input parameters, including predicting the fluidity, spreading area, flattening uniformity and other parameters of the solder. The output of the model or algorithm is the reflow flattening parameter, which reflects the solder flattening effect under the current reflow parameters.
[0037] In a possible implementation, step S400 further includes step S410, collecting a sample reflow parameter set, a sample impurity elimination parameter set, and a sample reflow flattening parameter set according to the processing data record of the reflow stage of the reflow soldering, wherein the sample reflow flattening parameter includes a flattening uniformity parameter of the solder joint after reflow. Specifically, the processing data record of the reflow soldering equipment in the reflow stage is accessed, including the changes of various parameters in the reflow soldering process, and the parameters related to the reflow stage, such as reflow temperature, reflow time, heating rate, etc., are extracted from the processing data record, and the impurity elimination parameters of the sample are extracted, and the flattening uniformity parameter of the solder joint after reflow is collected. The flattening uniformity parameter describes the distribution of solder on the surface of the solder joint, which is an important indicator for evaluating the reflow soldering effect. Step S420, using the sample reflow parameter set, the sample impurity elimination parameter set, and the sample reflow flattening parameter set, a reflow flattening predictor is trained, and the solder reflow flattening prediction is performed on the reflow parameters and the optimal impurity elimination parameters to obtain the reflow flattening parameters. Specifically, a reflow flattening predictor is trained using the sample parameter set collected in step S410 (including reflow parameters, impurity elimination parameters, and reflow flattening parameters). The reflow flattening predictor can be a machine learning model, such as a neural network, a random forest, etc. The reflow parameters to be predicted and the optimal impurity elimination parameters are input into the trained reflow flattening predictor. The reflow flattening predictor outputs the corresponding reflow flattening parameters based on the input parameters, that is, predicts the flattening uniformity of the solder joint after reflow soldering. This implementation method trains a reflow flattening predictor by collecting parameters in the reflow stage of the reflow soldering process, thereby achieving the technical effect of improving the efficiency and accuracy of solder reflow flattening prediction.
[0038] Step S500, when the reflux paving parameters do not meet the requirements of the preset threshold reflux paving parameters, calculate the reflux paving parameter deviation, set the reflux optimization step, optimize the reflux parameters, and obtain the optimal reflux parameters, wherein, during the optimization process, the reflux paving parameters are predicted based on the optimal impurity elimination parameters and the reflux parameters. Specifically, according to the process requirements and quality standards, a threshold reflux paving parameter is pre-set as a benchmark for judging whether the current reflux paving effect meets the standard, and the obtained reflux paving parameters are compared with the preset threshold reflux paving parameters. If the current reflux paving parameters are lower than the threshold value, the deviation between the current reflux paving parameters and the threshold value is calculated, and the deviation can be an absolute value, a percentage or other appropriate measurement method. According to the characteristics of the problem and the actual situation, select a suitable optimization algorithm, such as gradient descent method, genetic algorithm, particle swarm optimization algorithm, etc., and set a suitable reflux optimization step according to the requirements of the optimization algorithm and the sensitivity of the problem. The optimization process starts with the current reflow parameters as the initial value. In each iteration, the reflow parameters are adjusted according to the optimization algorithm and the set reflow optimization step size. Based on the adjusted reflow parameters and the optimal impurity elimination parameters, the model or algorithm is used to predict the new reflow leveling parameters, and evaluate whether the new reflow leveling parameters meet the requirements or are improved. If they meet the requirements or are improved, the current reflow parameters are recorded as the current optimal reflow parameters; otherwise, the iterative optimization continues. When certain end conditions are met (such as reaching the preset number of iterations, the optimization effect of multiple consecutive iterations is not obvious, etc.), the optimization process is stopped and the final optimal reflow parameters (parameters that can maximize the solder reflow leveling effect) are output.
[0039] In a possible implementation, step S500 further includes step S510, determining whether the reflow paving parameters meet the threshold reflow paving parameter requirements, if so, the reflow parameters are not optimized, if not, the reflow paving parameter deviation is calculated. Specifically, a threshold reflow paving parameter is set, and the threshold reflow paving parameter is a pre-set threshold parameter representing the acceptable range of solder joint paving quality. The predicted reflow paving parameters are compared with the threshold reflow paving parameters. If the reflow paving parameters meet the threshold requirements (i.e., within the acceptable range), it is determined to be qualified and the reflow parameters are not optimized; if the threshold requirements are not met (i.e., lower than or beyond the acceptable range), the next step is continued to calculate the deviation value between the reflow paving parameters and the threshold reflow paving parameters. Step S520, according to the reflow paving parameter deviation, the preset step length is corrected to obtain the reflow optimization step length. Specifically, according to the deviation value of the reflow paving parameter, the preset step value is corrected, and the corrected step value is the reflow optimization step value, which represents the step size or adjustment amount taken in each iteration or optimization in the reflow parameter adjustment. Step S530, constructing a reflow optimization function for optimizing the reflow parameters, as shown in the following formula: ; Among them, HF is the reflux fitness, To optimize the reflow parameters after reflow paving, is the threshold reflow leveling parameter. Specifically, the reflow optimization function is a function used to evaluate the quality of the reflow parameters, and is calculated based on the comparison result between the reflow leveling parameters and the threshold reflow leveling parameters. Step S540, optimize the reflow parameters according to the reflow optimization step and the reflow optimization function to obtain the optimal reflow parameters. Specifically, adjust the reflow parameters according to the reflow fitness value and the reflow optimization step, and repeat this process until the optimization stop condition is met (such as the reflow fitness reaches a preset threshold, the number of iterations reaches an upper limit, etc.), and the reflow parameter value in the last iteration is the optimal reflow parameter. This implementation method achieves the technical effect of finding the reflow parameters that achieve the best solder joint leveling quality through an iterative optimization method.
[0040] In a possible implementation, the reflow parameters are optimized according to the reflow optimization step and the reflow optimization function, and step S540 further includes step S541, using the reflow optimization step to adjust the reflow parameters to obtain the first reflow parameters. Specifically, the current reflow parameters (initial value or the result of the previous iteration) are obtained, and the reflow parameters are increased or decreased according to the reflow optimization step to obtain a new reflow parameter value, i.e., the first reflow parameter. Step S542, using the first reflow parameter, combined with the optimal impurity elimination parameter, reflow paving prediction is performed to obtain the first reflow paving parameter, and the first reflow fitness is calculated. Specifically, the first reflow parameter and the known optimal impurity elimination parameter are used as inputs, substituted into the reflow paving predictor, and the first reflow paving parameter is predicted. According to the first reflow paving parameter, the first reflow fitness is calculated as an indicator for evaluating the quality of the current reflow parameters. Step S543, determine whether the first reflow paving parameter is greater than the reflow paving parameter, if so, reduce the reflow optimization step length, if not, enlarge the reflow optimization step length, adjust the first reflow parameter, obtain the second reflow parameter, and predict and process to obtain the second reflow paving parameter and the second reflow fitness. Specifically, compare the first reflow paving parameter with the current reflow paving parameter. If the first reflow paving parameter is better (such as larger), it means that the current optimization direction is correct and needs more refined adjustment, so the reflow optimization step length is reduced (i.e., the step length is reduced); if the first reflow paving parameter is not as good as the current reflow paving parameter, it means that the current optimization direction may be wrong and needs more substantial adjustment, so the reflow optimization step length is enlarged (i.e., the step length is increased). According to the adjusted step length, adjust the first reflow parameter to obtain the second reflow parameter, repeat step S542, use the second reflow parameter for prediction and processing, and obtain the second reflow paving parameter and the second reflow fitness. Step S544, discriminate according to the second reflux fitness and the first reflux fitness, obtain the optimization basis, optimize until convergence, and output the final optimal reflux parameters. Specifically, this step is similar to steps S371-S372 and will not be repeated here. This implementation adopts the idea of iterative optimization. During the optimization process, by comparing the reflux paving parameters and reflux fitness under different parameters, it is determined whether the current optimization direction is correct, and the reflux optimization step size is adjusted as needed, thereby achieving the technical effect of realizing a fast and stable optimization process.
[0041] Step S600, based on the optimal preheating parameters, the optimal constant temperature parameters and the optimal reflow parameters, an optimized reflow process is generated. Specifically, the optimal preheating parameters, the optimal constant temperature parameters and the optimal reflow parameters are integrated into a new set of reflow processes, and these parameters together constitute the key parameters of the optimized reflow process. According to the integrated optimal parameters, a new reflow process is designed, including determining the temperature curve of the entire welding process (including the preheating stage, the constant temperature stage and the reflow stage), the transmission speed, the welding time and other key process parameters. Before the formal implementation of the optimized reflow process, simulation software or actual equipment can be used for simulation verification. According to the results of the simulation verification, the parameters of the reflow process are fine-tuned, including adjusting certain stages of the temperature curve, fine-tuning the transmission speed or welding time, etc., to further optimize the welding quality and improve production efficiency. The optimized reflow process after verification and fine-tuning is written into a process file for application in actual production. The embodiment of the present application adopts technical means such as collecting solder parameters and spot material images, identifying spot material specification information, predicting solder impurity elimination in combination with preheating parameters and constant temperature parameters, calculating impurity elimination parameter deviation, optimizing preheating parameters and constant temperature parameters, predicting solder reflow paving in combination with optimal impurity elimination parameters, and optimizing reflow parameters, thereby achieving the technical effect of improving the adaptability and flexibility of process parameters and improving the consistency and stability of welding quality through adaptive optimization of process parameters.
[0042] 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 method for adaptively optimizing reflow process parameters, characterized in that: The method comprises: Collect solder parameters for reflow soldering, collect solder spotting images after solder spotting, and identify and obtain spotting specification information; Collect the preheating parameters and constant temperature parameters in the current reflow soldering process, combine the solder parameters and the spot material specification information, perform solder impurity elimination prediction, and obtain solder impurity elimination parameters; When the solder impurity elimination parameter does not meet the requirement of the preset threshold impurity elimination parameter, the impurity elimination parameter deviation is calculated, the preparation optimization step is set, the preheating parameter and the constant temperature parameter are optimized, the optimal preheating parameter and the optimal constant temperature parameter are obtained, and the optimal impurity elimination parameter is obtained; Collect the reflow parameters in the current reflow soldering process, combine them with the optimal impurity elimination parameters, perform solder reflow leveling prediction, and obtain the reflow leveling parameters; When the reflux paving parameter does not meet the requirement of the preset threshold reflux paving parameter, calculating the reflux paving parameter deviation, setting the reflux optimization step, optimizing the reflux parameter, and obtaining the optimal reflux parameter, wherein, during the optimization process, the reflux paving parameter is predicted based on the optimal impurity elimination parameter and the reflux parameter; Based on the optimal preheating parameters, the optimal constant temperature parameters and the optimal reflow parameters, an optimized reflow soldering process is generated; When the solder impurity elimination parameter does not meet the requirement of the preset threshold impurity elimination parameter, the impurity elimination parameter deviation is calculated, the preparation optimization step is set, and the preheating parameter and the constant temperature parameter are optimized, including: Determine whether the solder impurity elimination parameter meets the requirement of the threshold impurity elimination parameter, if yes, do not optimize the preheating parameter and the constant temperature parameter, if not, calculate and obtain the impurity elimination parameter deviation; According to the impurity elimination parameter deviation, the preset step length is corrected to obtain a step length to be optimized; Construct a preparatory optimization function for optimizing the preheating parameters and constant temperature parameters as follows: ; Among them, PF is the preparation fitness, To optimize the impurity elimination parameters after preheating parameters and constant temperature parameters, is the threshold impurity elimination parameter; The preheating parameter and the constant temperature parameter are adjusted by using a preparation optimization step length to obtain a first preheating parameter and a first constant temperature parameter; Using the first preheating parameter and the first constant temperature parameter, combined with the solder parameter and the material specification information, to predict the solder impurity elimination, obtain the first impurity elimination parameter, and calculate the first preparation fitness; Determine whether the first impurity elimination parameter is greater than the solder impurity elimination parameter, if so, reduce the preparation optimization step length, if not, enlarge the preparation optimization step length, adjust the first preheating parameter and the first constant temperature parameter to obtain the second preheating parameter and the second constant temperature parameter, and predict and process to obtain the second impurity elimination parameter and the second preparation fitness; Performing a judgment based on the second preparation fitness and the first preparation fitness to obtain an optimization basis; Continue to optimize and update based on the optimization basis until convergence, and output the final optimal preheating parameters and optimal constant temperature parameters; When the reflow paving parameters do not meet the requirements of the preset threshold reflow paving parameters, calculating the reflow paving parameter deviation, setting the reflow optimization step, optimizing the reflow parameters, and obtaining the optimal reflow parameters, including: Determine whether the reflow paving parameter meets the requirement of the threshold reflow paving parameter, if yes, do not optimize the reflow parameter, if no, calculate and obtain the reflow paving parameter deviation; According to the reflow paving parameter deviation, the preset step length is corrected to obtain the reflow optimization step length; Construct a reflux optimization function to optimize the reflux parameters as follows: ; Among them, HF is the reflux fitness, To optimize the reflow parameters after reflow paving, Paving the way for threshold reflow parameters; According to the reflow optimization step size and the reflow optimization function, the reflow parameters are optimized to obtain the optimal reflow parameters.
2. The method for adaptively optimizing reflow process parameters according to claim 1, characterized in that: Collect solder parameters for reflow soldering, collect solder spotting images after solder spotting, and identify and obtain spotting specification information, including: Detecting the solder components for reflow soldering to obtain solder parameters, wherein the solder components include alloy, flux, and solvent; Collect the solder dotted image on the target circuit board; According to the data record of the circuit board reflow, a set of sample material point images is collected, and the material point specifications are marked, a set of sample material point specification information is obtained, and a material point specification identifier is trained; The dot material specification identifier is used to identify the dot material image to obtain dot material specification information.
3. The method for adaptively optimizing reflow process parameters according to claim 1, characterized in that: Collect the preheating parameters and constant temperature parameters in the current reflow process, combine the solder parameters and point material specification information, and predict the elimination of solder impurities, including: Collect sample solder parameter sets, sample material point specification information sets, sample preheating parameter sets and sample constant temperature parameter sets, and collect sample solder impurity elimination parameter sets based on preheating and constant temperature stage data under different preheating parameters, constant temperature parameters, solder parameters and material point specification information; The sample solder parameter set, sample material spotting specification information set, sample preheating parameter set and sample constant temperature parameter set are used as input, and the sample solder impurity elimination parameter set is used as output to train an impurity elimination predictor, and solder impurity elimination prediction is performed on the preheating parameters, constant temperature parameters, solder parameters and material spotting specification information to obtain solder impurity elimination parameters.
4. The method for adaptively optimizing reflow process parameters according to claim 1, characterized in that: The optimization basis is obtained by judging according to the second preparation fitness and the first preparation fitness, including: When the second preparation fitness is greater than the first preparation fitness, taking the second preheating parameter and the second constant temperature parameter as optimization basis; When the second preparation fitness is not greater than the first preparation fitness, the proximity between the second impurity elimination parameter and the first impurity elimination parameter is calculated. When the proximity is greater than a preset proximity threshold, the second preheating parameter and the second constant temperature parameter are used as the optimization basis. Otherwise, the first preheating parameter and the first constant temperature parameter are used as the optimization basis.
5. The method for adaptively optimizing reflow process parameters according to claim 1, characterized in that: Collect the reflow parameters in the current reflow soldering process, combine them with the optimal impurity elimination parameters, perform solder reflow leveling prediction, and obtain reflow leveling parameters, including: According to the processing data record of the reflow stage of the reflow soldering, a sample reflow parameter set, a sample impurity elimination parameter set, and a sample reflow paving parameter set are collected, wherein the sample reflow paving parameter includes a paving uniformity parameter of the solder joint after reflow; The sample reflow parameter set, the sample impurity elimination parameter set and the sample reflow leveling parameter set are used to train a reflow leveling predictor, and solder reflow leveling prediction is performed on the reflow parameters and the optimal impurity elimination parameters to obtain reflow leveling parameters.
6. The method for adaptively optimizing reflow process parameters according to claim 1, characterized in that: Optimizing the reflow parameters according to the reflow optimization step size and the reflow optimization function, including: Using the reflux optimization step length, adjusting the reflux parameters to obtain first reflux parameters; Using the first reflux parameter in combination with the optimal impurity elimination parameter, performing reflux paving prediction, obtaining a first reflux paving parameter, and calculating a first reflux fitness; Determine whether the first reflow flattening parameter is greater than the reflow flattening parameter, if so, reduce the reflow optimization step length, if not, enlarge the reflow optimization step length, adjust the first reflow parameter to obtain the second reflow parameter, and perform prediction processing to obtain the second reflow flattening parameter and the second reflow fitness; A judgment is made based on the second reflux fitness and the first reflux fitness to obtain an optimization basis, and the optimization is performed until convergence to output the final optimal reflux parameters.
Citation Information
Cited By
Protective mask 3D printing process parameter optimization method
CN120046514A
A Method for Optimizing 3D Printing Process Parameters of a Protective Face Mask
CN120046514B
