CN118428244B - Reflow soldering process parameter self-adaptive optimization method - Google Patents
Reflow soldering process parameter self-adaptive optimization method Download PDFInfo
- Publication number
- CN118428244B CN118428244B CN202410885439.0A CN202410885439A CN118428244B CN 118428244 B CN118428244 B CN 118428244B CN 202410885439 A CN202410885439 A CN 202410885439A CN 118428244 B CN118428244 B CN 118428244B
- Authority
- CN
- China
- Prior art keywords
- parameter
- reflow
- parameters
- solder
- impurity elimination
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 151
- 238000000034 method Methods 0.000 title claims abstract description 110
- 230000008569 process Effects 0.000 title claims abstract description 81
- 238000005476 soldering Methods 0.000 title claims abstract description 68
- 239000012535 impurity Substances 0.000 claims abstract description 172
- 229910000679 solder Inorganic materials 0.000 claims abstract description 162
- 230000008030 elimination Effects 0.000 claims abstract description 134
- 238000003379 elimination reaction Methods 0.000 claims abstract description 134
- 238000002360 preparation method Methods 0.000 claims abstract description 79
- 239000000463 material Substances 0.000 claims abstract description 68
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000010992 reflux Methods 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 10
- 230000004907 flux Effects 0.000 claims description 8
- 239000002904 solvent Substances 0.000 claims description 7
- 229910045601 alloy Inorganic materials 0.000 claims description 4
- 239000000956 alloy Substances 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 24
- 238000003466 welding Methods 0.000 abstract description 9
- 230000003044 adaptive effect Effects 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 description 22
- 230000006870 function Effects 0.000 description 16
- 238000010801 machine learning Methods 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 239000000126 substance Substances 0.000 description 4
- 229910000967 As alloy Inorganic materials 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 229910052751 metal Inorganic materials 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000001965 increasing effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 229910052709 silver Inorganic materials 0.000 description 2
- 239000004332 silver Substances 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000003892 spreading Methods 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 229910052718 tin Inorganic materials 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 239000002923 metal particle Substances 0.000 description 1
- 150000002739 metals Chemical class 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 229910052755 nonmetal Inorganic materials 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- -1 oxides Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 239000011135 tin Substances 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K1/00—Soldering, e.g. brazing, or unsoldering
- B23K1/0008—Soldering, e.g. brazing, or unsoldering specially adapted for particular articles or work
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K3/00—Tools, devices, or special appurtenances for soldering, e.g. brazing, or unsoldering, not specially adapted for particular methods
- B23K3/04—Heating appliances
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mechanical Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Electric Connection Of Electric Components To Printed Circuits (AREA)
Abstract
本发明公开了回流焊工艺参数自适应优化方法，涉及数据处理相关领域，该方法包括：采集焊料参数，获得点料规格信息；采集预热参数和恒温参数，进行焊料杂质消除预测，获得焊料杂质消除参数；计算杂质消除参数偏差，设置准备优化步长，进行优化，获得最优预热参数和最优恒温参数，获得最优杂质消除参数；采集回流参数，进行焊料回流铺平预测，获得回流铺平参数；计算回流铺平参数偏差，设置回流优化步长，进行优化，获得最优回流参数；生成优化回流焊工艺。解决了现有回流焊工艺参数调整存在的缺乏适应性调整，难以保证焊接质量可靠性和一致性的技术问题，达到了提高工艺参数的适应性和灵活性，提高焊接质量的一致性和稳定性的技术效果。
The present invention discloses a method for adaptively optimizing reflow soldering process parameters, which relates to data processing related fields. The method comprises: collecting solder parameters to obtain spot material specification information; collecting preheating parameters and constant temperature parameters to predict solder impurity elimination to obtain solder impurity elimination parameters; calculating impurity elimination parameter deviations, setting preparation optimization steps, optimizing to obtain optimal preheating parameters and optimal constant temperature parameters, and obtaining optimal impurity elimination parameters; collecting reflow parameters, predicting solder reflow flattening to obtain reflow flattening parameters; calculating reflow flattening parameter deviations, setting reflow optimization steps, optimizing to obtain optimal reflow parameters; and generating an optimized reflow soldering process. The method solves the technical problems of the lack of adaptive adjustment in the existing reflow soldering process parameter adjustment, and the difficulty in ensuring the reliability and consistency of welding quality, and achieves the technical effects of improving the adaptability and flexibility of process parameters, and improving the consistency and stability of welding quality.
Description
Technical Field
The application relates to the field of data processing, in particular to a reflow soldering process parameter self-adaptive optimization method.
Background
With the rapid development of electronic manufacturing industry, a reflow soldering process is a key step in the assembly process of electronic components, and the soldering quality directly affects the reliability and performance of the product. The existing reflow process parameter setting method mainly comprises parameter setting based on fixed process specifications and adjustment based on experience parameters, however, the adjustment method based on experience parameters is excessively dependent on the skills and experience of operators, is easily affected by human factors, lacks adaptive adjustment to real-time process conditions and solder characteristics, and is difficult to ensure consistency and stability of welding quality when facing complex production environments and changeable solder characteristics.
In the related art at the present stage, the adjustment of reflow process parameters lacks adaptability adjustment, and the technical problem that the reliability and consistency of the welding quality are difficult to ensure is solved.
Disclosure of Invention
The application adopts the technical means of collecting solder parameters and spot material images, identifying spot material specification information, carrying out solder impurity elimination prediction by combining preheating parameters and constant temperature parameters, calculating impurity elimination parameter deviation, optimizing the preheating parameters and the constant temperature parameters, carrying out solder reflow paving prediction by combining optimal impurity elimination parameters, optimizing reflow parameters and the like, thereby achieving the technical effects of improving the adaptability and the flexibility of the process parameters and improving the consistency and the stability of the welding quality by self-adaptively optimizing the process parameters.
The application provides a reflow soldering process parameter self-adaptive optimization method, which comprises the following steps:
Collecting solder parameters for reflow soldering, collecting a spot-material image after spot-material of the solder, and identifying to obtain spot-material specification information; collecting preheating parameters and constant temperature parameters in the current reflow soldering process, and carrying out solder impurity elimination prediction by combining the solder parameters and spot-size specification information to obtain solder impurity elimination parameters; when the solder impurity elimination parameter does not meet the requirement of a preset threshold impurity elimination parameter, calculating impurity elimination parameter deviation, setting a preparation optimization step length, optimizing the preheating parameter and the constant temperature parameter to obtain an optimal preheating parameter and an optimal constant temperature parameter, and obtaining an optimal impurity elimination parameter; collecting reflow parameters in the current reflow soldering process, and carrying out solder reflow paving prediction by combining the optimal impurity elimination parameters to obtain reflow paving parameters; when the reflow paving parameter does not meet the requirement of a preset threshold reflow paving parameter, calculating reflow paving parameter deviation, setting a reflow optimization step length, and optimizing the reflow parameter to obtain an optimal reflow parameter, wherein in the optimization process, the reflow paving parameter is predicted based on the optimal impurity elimination parameter and the reflow parameter; and generating an optimized reflow soldering process based on the optimal preheating parameter, the optimal constant temperature parameter and the optimal reflow parameter.
In a possible implementation manner, collecting solder parameters for reflow soldering, collecting a spot-material image after spot-material of the solder, identifying spot-material specification information, and executing the following processing:
detecting solder components for reflow soldering to obtain solder parameters, wherein the solder components comprise alloy, soldering flux and solvent; collecting a spot material image after solder spot material on a target circuit board; collecting a sample spot-material image set according to the data record of the circuit board reflow soldering, marking spot-material specifications, obtaining a sample spot-material specification information set, and training a spot-material specification identifier; and identifying the spot material image by adopting the spot material specification identifier to obtain spot material specification information.
In a possible implementation manner, preheating parameters and constant temperature parameters in the current reflow soldering process are collected, solder impurity elimination prediction is performed by combining the solder parameters and spot-size specification information, and the following processing is performed:
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 preheating and constant temperature stage data under different preheating parameters, constant temperature parameters, solder parameters and spot material specification information; and taking the sample solder parameter set, the sample spot material specification information set, the sample preheating parameter set and the sample constant temperature parameter set as inputs, taking the sample solder impurity elimination parameter set as outputs, training an impurity elimination predictor, and carrying out solder impurity elimination prediction on the preheating parameter, the constant temperature parameter, the solder parameter and the spot material specification information to obtain solder impurity elimination parameters.
In a possible implementation manner, when the solder impurity removal parameter does not meet the requirement of the preset threshold impurity removal parameter, calculating an impurity removal parameter deviation, setting a preparation optimization step length, optimizing the preheating parameter and the constant temperature parameter, and executing the following processing:
Judging whether the solder impurity elimination parameter meets the requirement of a threshold impurity elimination parameter, if so, not optimizing the preheating parameter and the constant temperature parameter, and if not, calculating to obtain impurity elimination parameter deviation; correcting the preset step length according to the impurity elimination parameter deviation to obtain a preparation optimization step length; and constructing a preparation optimization function for optimizing the preheating parameter and the constant temperature parameter, wherein the preparation optimization function comprises the following formula: ; wherein PF is the preparation fitness, In order to optimize the impurity elimination parameters after the preheating parameters and the constant temperature parameters,Is a threshold impurity elimination parameter; adopting a preparation optimization step length to adjust the preheating parameter and the constant temperature parameter to obtain a first preheating parameter and a first constant temperature parameter; adopting the first preheating parameter and the first constant temperature parameter, combining the solder parameter and spot material specification information, carrying out solder impurity elimination prediction to obtain a first impurity elimination parameter, and calculating to obtain a first preparation fitness; judging whether the first impurity elimination parameter is larger than the solder impurity elimination parameter, if so, reducing the preparation optimization step length, if not, amplifying the preparation optimization step length, adjusting the first preheating parameter and the first constant temperature parameter to obtain a second preheating parameter and a second constant temperature parameter, and predicting to obtain a second impurity elimination parameter and a second preparation fitness; judging according to the second preparation fitness and the first preparation fitness to obtain an optimization basis; and continuously optimizing and updating to convergence based on the optimization basis, and outputting the final optimal preheating parameters and the optimal constant temperature parameters.
In a possible implementation manner, the second preparation fitness and the first preparation fitness are judged according to the second preparation fitness, an optimization basis is obtained, and the following processing is executed:
When the second preparation fitness is larger than the first preparation fitness, taking the second preheating parameter and the second constant temperature parameter as optimization bases; and when the second preparation fitness is not greater than the first preparation fitness, calculating the adjacency of the second impurity elimination parameter and the first impurity elimination parameter, and when the adjacency is greater than a preset adjacency threshold, taking the second preheating parameter and the second constant temperature parameter as optimization bases, otherwise, taking the first preheating parameter and the first constant temperature parameter as optimization bases.
In a possible implementation manner, collecting reflow parameters in the current reflow soldering process, carrying out solder reflow paving prediction by combining the optimal impurity elimination parameters to obtain reflow paving parameters, and executing the following processing:
Collecting a sample reflow parameter set and a sample impurity elimination parameter set according to processing data records of a reflow stage of reflow soldering, and collecting a sample reflow paving parameter set, wherein the sample reflow paving parameter comprises a paving uniformity parameter of a solder joint after reflow; training a reflow paving predictor by adopting the sample reflow parameter set, the sample impurity eliminating parameter set and the sample reflow paving parameter set, and carrying out solder reflow paving prediction on the reflow parameters and the optimal impurity eliminating parameters to obtain reflow paving parameters.
In a possible implementation manner, when the reflow soldering parameter does not meet the requirement of a preset threshold reflow soldering parameter, calculating a reflow soldering parameter deviation, setting a reflow optimization step length, optimizing the reflow parameter to obtain an optimal reflow parameter, and executing the following processing:
Judging whether the reflow paving parameters meet the requirements of threshold reflow paving parameters, if so, not optimizing the reflow parameters, and if not, calculating to obtain reflow paving parameter deviation; correcting a preset step length according to the reflow paving parameter deviation to obtain a reflow optimization step length; constructing a reflux optimization function for optimizing reflux parameters, wherein the reflux optimization function comprises the following formula: ; wherein HF is reflux fitness, To optimize the reflow flattening parameters after the reflow parameters,Paving parameters for threshold reflux; and optimizing the reflow parameters according to the reflow optimization step length and the reflow optimization function to obtain the optimal reflow parameters.
In a possible implementation manner, according to the reflow optimization step size and the reflow optimization function, the reflow parameters are optimized, and the following processing is performed:
Adopting the reflux optimization step length to adjust the reflux parameter to obtain a first reflux parameter; adopting the first reflow parameters, combining the optimal impurity elimination parameters, carrying out reflow paving prediction to obtain first reflow paving parameters, and calculating to obtain first reflow fitness; judging whether the first reflow paving parameter is larger than the reflow paving parameter, if so, reducing the reflow optimization step length, if not, amplifying the reflow optimization step length, adjusting the first reflow parameter to obtain a second reflow parameter, and predicting to obtain a second reflow paving parameter and a second reflow fitness; and judging according to the second reflux fitness and the first reflux fitness to obtain an optimization basis, optimizing until convergence, and outputting a final optimal reflux parameter.
The application provides a reflow process parameter self-adaptive optimization method, which comprises the steps of firstly collecting solder parameters for reflow soldering, collecting spot material images after spot material of the solder, identifying spot material specification information, then collecting preheating parameters and constant temperature parameters in the current reflow process, combining the solder parameters and the spot material specification information, carrying out solder impurity elimination prediction to obtain solder impurity elimination parameters, calculating impurity elimination parameter deviation when the solder impurity elimination parameters do not meet the requirements of preset threshold impurity elimination parameters, setting a preparation optimization step length, optimizing the preheating parameters and constant temperature parameters to obtain optimal preheating parameters and optimal constant temperature parameters, obtaining optimal impurity elimination parameters, collecting reflow parameters in the current reflow process, carrying out solder reflow paving prediction to obtain reflow paving parameters, then calculating reflow paving parameter deviation when the reflow paving parameters do not meet the requirements of the preset threshold reflow paving parameters, setting a reflow optimization step length, optimizing the reflow parameters to obtain optimal reflow parameters, wherein in the optimization process, finally, carrying out constant temperature prediction on the reflow parameters based on the optimal elimination parameters and the reflow parameters, generating the optimal reflow parameters, and achieving the self-adaptive quality and the optimization effect by the optimization process parameters.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present application, the following description will briefly refer to the accompanying drawings of the embodiments of the present application, in which flowcharts are used to illustrate operations performed by systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Fig. 1 is a schematic flow chart of a method for adaptively optimizing reflow process parameters according to an embodiment of the present application.
Fig. 2 is a schematic flow chart of optimizing preheating parameters and constant temperature parameters in the reflow process parameter adaptive optimization method according to the embodiment of the application.
Detailed Description
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be 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, the term "first\second" being referred to merely as distinguishing between similar objects and not representing a particular ordering for the objects. The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules that may not be expressly listed or inherent to such process, method, article, or apparatus, and unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used herein is for the purpose of describing embodiments of the application only.
The embodiment of the application provides a reflow process parameter self-adaptive optimization method, as shown in fig. 1, comprising the following steps:
And S100, collecting solder parameters for reflow soldering, collecting spot-material images after spot-material of the solder, and identifying to obtain spot-material specification information. Specifically, the measurement of physical and chemical parameters of solder (materials used to solder two or more metals or metal and non-metal surfaces) is performed using sensors, analytical instruments, etc., including, but not limited to, the melting point of the solder, the component proportions (e.g., alloy components such as tin, silver, copper, etc.), the particle size, the viscosity, the thermal conductivity, etc. After the solder is dispensed, an image of a dispensing area, namely an image of the actual distribution condition of the solder on a Printed Circuit Board (PCB), is shot by using equipment such as a high-definition camera, a microscope and the like, the dispensing image is processed by using image processing software, the steps of denoising, enhancing contrast, edge detection and the like are included, the image quality is improved, the characteristics of the dispensing are highlighted, characteristic information of the dispensing, such as the shape, the size, the number, the spacing and the like of the dispensing, is extracted from the processed image, and the dispensing specification is identified by using a machine learning or deep learning algorithm according to the extracted characteristic information, wherein the detailed information comprises the type, the size range, the distribution condition and the like of the dispensing.
In one possible implementation, step S100 further includes step S110, detecting solder components for reflow soldering, where the solder components include an alloy, a flux, and a solvent, to obtain solder parameters. Specifically, a representative sample is selected from the solder to be soldered, and key parameters such as alloy components (main metal components in the solder, such as tin, lead, silver, etc.), types and contents of soldering flux (substances which help to remove oxides, reduce surface tension, promote intermetallic diffusion during soldering), types and contents of solvent (a part of the soldering flux, which is used for dissolving other components in the soldering flux, and volatilized during soldering) and the like in the solder sample are detected by using a chemical analysis or spectroscopic analysis method and the like, and the detected solder parameters such as alloy proportion, types and contents of the soldering flux and the solvent, and the like are recorded in detail. Step S120, collecting a spot material image after solder spot material on the target circuit board. Specifically, a circuit board to be soldered (a substrate for electronic component mounting) is placed at a suitable position, solder is dispensed at a specified position of a target circuit board using a dispenser or other equipment, and a solder dispensing image on the circuit board is photographed using a high-resolution camera or camera. Step S130, collecting a sample spot-size image set according to the data record of the circuit board reflow soldering, marking spot-size specifications, obtaining a sample spot-size specification information set, and training a spot-size specification identifier. Specifically, spot material images with different spot material specifications are selected from the data record of the circuit board reflow soldering to form a sample spot material image set, and each image in the sample spot material image set is marked with spot material specifications (characteristic parameters such as the shape, the size, the position and the like of a solder spot on the circuit board) to form a sample spot material specification information set. Selecting a machine learning algorithm suitable for image recognition, such as Convolutional Neural Network (CNN), using the sample spot size image set and the corresponding sample spot size specification information set, training a spot size specification identifier capable of automatically identifying and classifying spot size specifications on the circuit board. And step S140, identifying the spot material image by adopting the spot material specification identifier to obtain spot material specification information. Specifically, the spot-size image acquired in step S120 is input into a spot-size identifier, and the spot-size identifier processes and analyzes the input image to identify spot-size specification information. According to the implementation mode, the spot material specification identifier is trained, so that automatic identification of spot material specifications is realized, manual operation and errors are reduced, and the technical effects of improving identification accuracy and efficiency are achieved.
Step S200, collecting preheating parameters and constant temperature parameters in the current reflow soldering process, and carrying out solder impurity elimination prediction by combining the solder parameters and spot-size specification information to obtain solder impurity elimination parameters. Specifically, data of a preheating parameter (parameters such as a temperature, a time, etc. for heating solder before reflow, such as a preheating temperature, a preheating time, etc.) and a constant temperature parameter (parameters for keeping the solder temperature stable after preheating, such as a constant temperature, a constant temperature time, etc.) in the current reflow process are collected in real time using a sensor or an apparatus control system. Based on historical data and experience, a suitable model or algorithm is selected or trained to predict the degree of impurity removal in the solder, either a model based on physical principles or a model trained by machine learning or deep learning. The method comprises the steps of inputting the currently collected preheating parameters, constant temperature parameters, solder parameters and spot material specification information into a model or algorithm, running the model or algorithm, and calculating the impurity elimination degree of the solder in the preheating and constant temperature processes (unnecessary substances such as solvents, oxides, metal particles and the like mixed into the solder in the welding process) based on the input parameters, wherein the impurity elimination degree comprises the volatilization amount of the solvents in the predicted solder, the residual quantity of the impurities and the like, and the output of the model or algorithm is the solder impurity elimination parameter (the parameter for predicting the impurity elimination degree in the solder), such as impurity elimination rate and the like.
In one possible implementation, step S200 further includes step S210 of collecting a sample solder parameter set, a sample spot size information set, a sample preheating parameter set, and a sample constant temperature parameter set, and collecting a sample solder impurity removal parameter set according to preheating and constant temperature stage data under different preheating parameters, constant temperature parameters, solder parameters, and spot size information. Specifically, historical soldering data is collected, including solder parameters (such as alloy composition, flux type, etc.), spot size information (such as spot size, shape, etc.), preheating parameters (such as preheating temperature, time, etc.), and constant temperature parameters (such as constant temperature, time, etc.), and relevant data of solder impurity removal conditions recorded at the preheating and constant temperature stages according to the different preheating parameters, constant temperature parameters, solder parameters, and spot size information, such as impurity type, quantity, distribution, etc., which constitute a sample solder impurity removal parameter set. And classifying and sorting the collected data according to different parameter combinations to form a one-to-one corresponding sample data set. Step S220, adopting the sample solder parameter set, the sample spot material specification information set, the sample preheating parameter set and the sample constant temperature parameter set as inputs, adopting the sample solder impurity elimination parameter set as outputs, training an impurity elimination predictor, and carrying out solder impurity elimination prediction on the preheating parameter, the constant temperature parameter, the solder parameter and the spot material specification information to obtain solder impurity elimination parameters. Specifically, according to the characteristics of the problem, a suitable machine learning or deep learning algorithm, such as a Support Vector Machine (SVM), a random forest, or a neural network, is selected, necessary preprocessing, such as data cleaning, normalization, encoding, etc., is performed on the sample data collected in step S210, the preprocessed sample data is used as input, the corresponding sample solder impurity removal parameter is used as output, the impurity removal predictor is trained, and the impurity removal predictor can predict solder impurity removal conditions according to given preheating parameters, constant temperature parameters, solder parameters, and spot material specification information, and output solder impurity removal parameters. According to the implementation mode, the prediction model is established, so that automatic prediction of the solder impurity elimination parameter is realized, and the technical effects of improving the accuracy and efficiency of the solder impurity elimination prediction are achieved.
And step S300, when the solder impurity elimination parameter does not meet the requirement of a preset threshold impurity elimination parameter, calculating impurity elimination parameter deviation, setting a preparation optimization step length, optimizing the preheating parameter and the constant temperature parameter to obtain an optimal preheating parameter and an optimal constant temperature parameter, and obtaining an optimal impurity elimination parameter. Specifically, a threshold impurity elimination parameter is preset according to the process requirements and quality standards and is used as a reference for judging whether the current impurity elimination effect meets the standard. Comparing the obtained solder impurity elimination parameter with a preset threshold impurity elimination parameter, if the current solder impurity elimination parameter is lower than the threshold value, calculating the deviation between the current solder impurity elimination parameter and the threshold value, wherein the deviation can be an absolute value, a percentage or other proper measurement modes. According to the characteristics and actual conditions of the problems, a proper optimization algorithm, such as a gradient descent method, a genetic algorithm, a particle swarm optimization algorithm and the like, is selected, and a proper preparation optimization step length is set according to the requirements of the optimization algorithm and the sensitivity of the problems. And starting an optimization process by taking the current preheating parameter and the constant temperature parameter as initial values, carrying out iterative adjustment on the preheating parameter and the constant temperature parameter according to an optimization algorithm and a set preparation optimization step length, and in each iteration, recalculating the solder impurity elimination parameter according to the adjusted parameter and evaluating whether the solder impurity elimination parameter meets the requirement, if a certain group of parameters are found to generate better impurity elimination effect (namely, the solder impurity elimination parameter is higher) in the optimization process, recording the group of parameters as the current optimal parameter, and stopping the optimization process when a certain ending condition is met (such as reaching a preset iteration number, unobvious continuous repeated iterative optimization effect and the like), and outputting the finally obtained optimal preheating parameter, optimal constant temperature parameter and the corresponding optimal impurity elimination parameter.
As shown in fig. 2, in one possible implementation manner, when the solder impurity removal parameter does not meet the requirement of the preset threshold impurity removal parameter, calculating an impurity removal parameter deviation, setting a preparation optimization step, optimizing the preheating parameter and the constant temperature parameter, and step S300 further includes step S310 of determining whether the solder impurity removal parameter meets the requirement of the threshold impurity removal parameter, if yes, not optimizing the preheating parameter and the constant temperature parameter, and if not, calculating to obtain the impurity removal parameter deviation. Specifically, comparing the current solder impurity removal parameter with a preset threshold impurity removal parameter (a standard value or a lowest acceptable value of the preset solder impurity removal parameter), and if the current solder impurity removal parameter meets or exceeds a threshold value, not optimizing the preheating parameter and the constant temperature parameter; if not, the next step is carried out, and the deviation value of the current solder impurity elimination parameter and the threshold impurity elimination parameter is calculated. Step S320, correcting the preset step length according to the impurity elimination parameter deviation to obtain a preparation optimization step length. Specifically, based on impurity elimination parameter deviation and other factors (such as historical data, system stability and the like), the preset step length is corrected to obtain a preparation optimization step length, wherein the preparation optimization step length is the step length for subsequently adjusting the preheating parameter and the constant temperature parameter. Step S330, constructing a preparation optimization function for optimizing the preheating parameter and the constant temperature parameter, wherein the preparation optimization function comprises the following formula: ; wherein PF is the preparation fitness, In order to optimize the impurity elimination parameters after the preheating parameters and the constant temperature parameters,Is a threshold impurity removal parameter. Specifically, the preparation optimization function is a mathematical function for guiding the optimization process of the preheating parameter and the constant temperature parameter, and the preparation fitness is an index for evaluating the quality of the solder impurity elimination effect under the optimization of the preheating parameter and the constant temperature parameter setting. And step S340, adopting a preparation optimization step length to adjust the preheating parameter and the constant temperature parameter, and obtaining a first preheating parameter and a first constant temperature parameter. Specifically, the preheating parameters and the constant temperature parameters are adjusted by using the preparation optimization step length, and the adjusted parameters are the first preheating parameters and the first constant temperature parameters. And S350, carrying out solder impurity elimination prediction by adopting the first preheating parameter and the first constant temperature parameter and combining the solder parameter and spot size specification information to obtain a first impurity elimination parameter, and calculating to obtain a first preparation fitness. Specifically, a first preheating parameter and a first constant temperature parameter are used, the solder parameter and spot size information are combined, a new impurity elimination parameter is predicted by an impurity elimination predictor, and a first preparation fitness is calculated by preparing an optimization function according to a prediction result and a threshold impurity elimination parameter. Step S360, judging whether the first impurity elimination parameter is larger than the solder impurity elimination parameter, if yes, reducing the preparation optimization step length, if not, amplifying the preparation optimization step length, adjusting the first preheating parameter and the first constant temperature parameter to obtain a second preheating parameter and a second constant temperature parameter, and predicting to obtain a second impurity elimination parameter and a second preparation fitness. Specifically, comparing the first impurity removal parameter with the solder impurity removal parameter, and if the first impurity removal parameter is more optimal, reducing the preparation optimization step length; if not, the preparation optimization step needs to be enlarged. And after adjusting the preparation optimization step length, adjusting the preheating parameter and the constant temperature parameter again to obtain a second preheating parameter and a second constant temperature parameter, and predicting to obtain a second impurity elimination parameter and a second preparation fitness. And step S370, judging according to the second preparation fitness and the first preparation fitness to obtain an optimization basis. Specifically, the first preparation fitness and the second preparation fitness are compared, and the direction and strategy of the subsequent optimization are determined based on the comparison result of the preparation fitness. And step S380, continuing to optimize and update to convergence based on the optimization basis, and outputting the final optimal preheating parameters and the optimal constant temperature parameters. Specifically, based on the optimization basis, the preheating parameters and the constant temperature parameters are continuously optimized and updated until convergence conditions are met (for example, the improvement of the preparation adaptability is no longer obvious or the preset maximum iteration times are reached), and the final optimal preheating parameters and the optimal constant temperature parameters are output. According to the implementation mode, through accurate prediction and iterative optimization, the optimal preheating parameter and constant temperature parameter combination is approximated gradually, and the technical effect of realizing accurate and efficient optimization is achieved.
In a possible implementation manner, step S370 further includes step S371, where 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 bases. Specifically, comparing the second preparation fitness with the first preparation fitness, if the second preparation fitness is greater than the first preparation fitness, it is indicated that the effect of the second set of parameters is better, and therefore the second preheating parameter and the second constant temperature parameter are used as the basis for the following optimization. Step S372, when the second preparation fitness is not greater than the first preparation fitness, calculating the adjacency of the second impurity elimination parameter and the first impurity elimination parameter, and when the adjacency is greater than a preset adjacency threshold, taking the second preheating parameter and the second constant temperature parameter as optimization bases, otherwise, taking the first preheating parameter and the first constant temperature parameter as optimization bases. Specifically, if the second preparation fitness is not greater than the first preparation fitness, further calculating the proximity of the two impurity removal parameters, where the proximity refers to the similarity or the proximity between the two impurity removal parameters, and may be calculated by using a difference value or other similarity measurement method, if the proximity is greater than a preset proximity threshold, it is indicated that the two impurity removal parameters are very close, and to avoid instability caused by frequent switching parameters, the second set of parameters is still selected as an optimization basis; if the proximity is not greater than a preset proximity threshold, the first set of parameters is selected as the basis for optimization because the second set of parameters does not significantly improve the impurity removal effect and the difference is large. By presetting the proximity threshold, the implementation method allows certain flexibility to be maintained in the parameter selection process, and even if the preparation adaptability of the second group of parameters is slightly low, if the two groups of parameters are very close, the second group of parameters can still be selected as an optimization basis to explore more possibilities, so that the technical effect of improving the flexibility of the optimization process is achieved.
And S400, collecting reflow parameters in the current reflow soldering process, and carrying out solder reflow paving prediction by combining the optimal impurity elimination parameters to obtain reflow paving parameters. Specifically, reflow parameters (reflow temperature, reflow time, reflow speed, etc.) data in the current reflow soldering process are collected in real time using a sensor or device control system. Based on historical data and experience, a suitable model or algorithm is selected to predict the spreading effect of the solder during reflow, either a model based on physical principles or a model trained by machine learning or deep learning. The current collected reflow parameters, the optimal impurity elimination parameters, the solder parameters and spot material specification information are used as input, the input is input into a model or algorithm, the model or algorithm is operated, the leveling effect of the solder in the reflow process is calculated based on the input parameters, the parameters such as fluidity, spreading area and leveling uniformity of the solder are predicted, the output of the model or algorithm is the reflow leveling parameters, and the reflow leveling parameters reflect the solder leveling effect under the current reflow parameters.
In one possible implementation, step S400 further includes step S410, collecting a sample reflow parameter set, a sample impurity removal parameter set, and a sample reflow paving parameter set according to a processing data record of a reflow stage of reflow soldering, wherein the sample reflow paving parameter includes a paving uniformity parameter of a solder joint after reflow. Specifically, a processing data record of reflow soldering equipment in a reflow stage is accessed, the processing data record contains the change condition of various parameters in the reflow soldering process, parameters related to the reflow stage, such as reflow temperature, reflow time, heating rate and the like, are extracted from the processing data record, impurity elimination parameters of a sample are extracted, leveling uniformity parameters of solder joints after reflow are collected, the leveling uniformity parameters describe the distribution condition of solder on the surface of the solder joints, and the processing data record is an important index for evaluating the reflow soldering effect. And S420, training a reflow paving predictor by adopting the sample reflow parameter set, the sample impurity elimination parameter set and the sample reflow paving parameter set, and carrying out solder reflow paving prediction on the reflow parameters and the optimal impurity elimination parameters to obtain reflow paving parameters. Specifically, using the sample parameter set (including the reflow parameters, the impurity removal parameters, and the reflow flattening parameters) collected in step S410, a reflow flattening predictor, which may be a machine learning model, such as a neural network, a random forest, or the like, is trained. And inputting the reflow parameters to be predicted and the optimal impurity elimination parameters into a trained reflow paving predictor, and outputting corresponding reflow paving parameters by the reflow paving predictor according to the input parameters, namely, predicting the paving uniformity of welding spots after reflow soldering. According to the implementation mode, the reflow soldering process reflow stage parameters are collected, a reflow soldering predictor is trained, and the technical effects of improving the efficiency and accuracy of solder reflow soldering prediction are achieved.
And S500, calculating a reflow paving parameter deviation when the reflow paving parameter does not meet the requirement of a preset threshold reflow paving parameter, setting a reflow optimization step length, and optimizing the reflow parameter to obtain an optimal reflow parameter, wherein in the optimization process, the reflow paving parameter is predicted based on the optimal impurity elimination parameter and the reflow parameter. Specifically, a threshold reflow paving parameter is preset according to the process requirement and the quality standard, the threshold reflow paving parameter is used as a reference for judging whether the current reflow paving effect meets the standard, the obtained reflow paving parameter is compared with the preset threshold reflow paving parameter, if the current reflow paving parameter is lower than the threshold value, the deviation between the current reflow paving parameter and the threshold value is calculated, and the deviation can be an absolute value, a percentage or other proper measurement modes. According to the characteristics and actual conditions of the problems, a proper optimization algorithm, such as a gradient descent method, a genetic algorithm, a particle swarm optimization algorithm and the like, is selected, and a proper reflux optimization step length is set according to the requirements of the optimization algorithm and the sensitivity of the problems. Starting an optimization process by taking a current reflow parameter as an initial value, adjusting the reflow parameter according to an optimization algorithm and a set reflow optimization step length in each iteration, predicting a new reflow paving parameter by using a model or algorithm based on the adjusted reflow parameter and combining with an optimal impurity elimination parameter, evaluating whether the new reflow paving parameter meets the requirement or is improved, and if the new reflow paving parameter meets the requirement or is improved, recording the current reflow parameter as the current optimal reflow parameter; otherwise, continuing the iterative optimization. When a certain end condition is met (for example, the preset iteration times are reached, the continuous repeated iteration optimization effect is not obvious, and the like), the optimization process is stopped, and finally the obtained optimal reflow parameters (parameters capable of maximizing the solder reflow paving effect) are output.
In a possible implementation manner, step S500 further includes step S510, determining whether the reflow soldering parameter meets a requirement of a threshold reflow soldering parameter, if so, not optimizing the reflow parameter, and if not, calculating to obtain a reflow soldering parameter deviation. Specifically, a threshold reflow paving parameter is set, and the threshold reflow paving parameter is a preset threshold parameter which represents an acceptable range of solder joint paving quality. Comparing the predicted reflow paving parameter with a threshold reflow paving parameter, and if the reflow paving parameter meets the threshold requirement (namely is within an acceptable range), judging that the reflow paving parameter is qualified, and not optimizing the reflow parameter; if the threshold requirement is not met (i.e., is below or exceeds the acceptable range), then the next step is continued to calculate the deviation value of the reflow paving parameter and the threshold reflow paving parameter. And step S520, correcting the preset step length according to the reflow paving parameter deviation to obtain a 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, which represents the step or adjustment amount adopted by each iteration or optimization in the reflow parameter adjustment. Step S530, constructing a reflow optimization function for optimizing the reflow parameters, wherein the reflow optimization function is as follows: ; wherein HF is reflux fitness, To optimize the reflow flattening parameters after the reflow parameters,Parameters are paved for threshold reflow. Specifically, the reflow optimization function is a function for evaluating the goodness of the reflow parameters, and is calculated based on the comparison of the reflow paving parameters with the threshold reflow paving parameters. And step S540, optimizing the reflow parameters according to the reflow optimization step length and the reflow optimization function to obtain the optimal reflow parameters. Specifically, according to the reflux fitness value and the reflux optimization step length, the reflux parameter is adjusted, the process is repeatedly performed until the optimization stopping condition is met (for example, the reflux fitness reaches a preset threshold value, the iteration number reaches an upper limit, and the like), and the reflux parameter value in the last iteration is the optimal reflux parameter. The implementation method achieves the technical effect of finding the reflux parameter which enables the paving quality of the welding spots to be optimal through an iterative optimization method.
In a possible implementation manner, the reflow parameters are optimized according to the reflow optimization step size and the reflow optimization function, and step S540 further includes step S541 of adjusting the reflow parameters with the reflow optimization step size to obtain the first reflow parameters. Specifically, the current reflow parameter (initial value or last iteration result) is obtained, and the reflow parameter is increased or decreased according to the reflow optimization step length, so as to obtain a new reflow parameter value, namely the first reflow parameter. And S542, carrying out reflow paving prediction by adopting the first reflow parameters and combining the optimal impurity elimination parameters to obtain first reflow paving parameters, and calculating to obtain first reflow fitness. Specifically, the first reflow parameters and the known optimal impurity elimination parameters are used as inputs and are substituted into a reflow paving predictor to predict and obtain the first reflow paving parameters, and the first reflow fitness is calculated according to the first reflow paving parameters and is used as an index for evaluating the quality of the current reflow parameters. And S543, judging whether the first reflow paving parameter is larger than the reflow paving parameter, if so, reducing the reflow optimization step length, if not, amplifying the reflow optimization step length, adjusting the first reflow parameter to obtain a second reflow parameter, and predicting to obtain the second reflow paving parameter and the second reflow fitness. Specifically, comparing the first reflow paving parameter with the current reflow paving parameter, if the first reflow paving parameter is better (e.g., larger), indicating that the current optimization direction is correct, requiring finer adjustment, and thus reducing the reflow optimization step size (i.e., reducing the step size); if the first reflow flattening parameter is not as good as the current reflow flattening parameter, indicating that the current optimization direction may not be right, a larger adjustment is required, thus enlarging the reflow optimization step size (i.e., increasing the step size). And according to the adjusted step length, the first reflow parameters are adjusted to obtain second reflow parameters, step S542 is repeated, and the second reflow parameters are used for prediction and processing to obtain second reflow paving parameters and second reflow fitness. And step S544, judging according to the second reflux fitness and the first reflux fitness to obtain an optimization basis, optimizing until convergence, and outputting a final optimal reflux parameter. Specifically, this step is similar to steps S371-S372, and will not be described here again. The implementation mode adopts the iterative optimization idea, in the optimization process, whether the current optimization direction is correct or not is judged by comparing the reflow flattening parameters and the reflow fitness under different parameters, and the reflow optimization step length is adjusted according to the needs, so that the technical effect of realizing the rapid and stable optimization process is achieved.
And step S600, generating an optimized reflow soldering process based on the optimal preheating parameter, the optimal constant temperature parameter and the optimal reflow parameter. Specifically, the optimal preheating parameter, the optimal constant temperature parameter and the optimal reflow parameter are integrated into a new reflow soldering process, and the parameters together form key parameters for optimizing the reflow soldering process. According to the integrated optimal parameters, a new reflow soldering process is designed, which comprises the steps of determining key process parameters such as a temperature curve (comprising a preheating stage, a constant temperature stage and a reflow stage), a conveying speed, a soldering time and the like of the whole soldering process. Before formally implementing the optimized reflow soldering process, simulation software or actual equipment can be used for simulation verification, and parameters of the reflow soldering process are finely adjusted according to the simulation verification result, including adjusting certain stages of a temperature curve, finely adjusting a conveying speed or soldering time, and the like, so that the soldering quality is further optimized, and the production efficiency is improved. And writing the optimized reflow soldering process after verification and fine adjustment into a process file so as to be applied to actual production. The embodiment of the application adopts the technical means of collecting solder parameters and spot material images, identifying spot material specification information, carrying out solder impurity elimination prediction by combining preheating parameters and constant temperature parameters, calculating impurity elimination parameter deviation, optimizing the preheating parameters and the constant temperature parameters, carrying out solder reflow paving prediction by combining optimal impurity elimination parameters, optimizing reflow parameters and the like, and achieves the technical effects of improving the adaptability and the flexibility of the process parameters and the consistency and the stability of welding quality by self-adaptively optimizing the process parameters.
The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, and alternatives are possible, depending on 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 scope of the present application. In some cases, the acts or steps recited in the present application may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Claims (6)
1. A method for adaptively optimizing reflow process parameters, the method comprising:
Collecting solder parameters for reflow soldering, collecting a spot-material image after spot-material of the solder, and identifying to obtain spot-material specification information;
Collecting preheating parameters and constant temperature parameters in the current reflow soldering process, and carrying out solder impurity elimination prediction by combining the solder parameters and spot-size specification information to obtain solder impurity elimination parameters;
when the solder impurity elimination parameter does not meet the requirement of a preset threshold impurity elimination parameter, calculating impurity elimination parameter deviation, setting a preparation optimization step length, optimizing the preheating parameter and the constant temperature parameter to obtain an optimal preheating parameter and an optimal constant temperature parameter, and obtaining an optimal impurity elimination parameter;
collecting reflow parameters in the current reflow soldering process, and carrying out solder reflow paving prediction by combining the optimal impurity elimination parameters to obtain reflow paving parameters;
When the reflow paving parameter does not meet the requirement of a preset threshold reflow paving parameter, calculating reflow paving parameter deviation, setting a reflow optimization step length, and optimizing the reflow parameter to obtain an optimal reflow parameter, wherein in the optimization process, the reflow paving parameter is predicted based on the optimal impurity elimination parameter and the reflow parameter;
generating an optimized reflow soldering process based on the optimal preheating parameter, the optimal constant temperature parameter and the optimal reflow parameter;
When the solder impurity elimination parameter does not meet the requirement of a preset threshold impurity elimination parameter, calculating impurity elimination parameter deviation, setting a preparation optimization step length, and optimizing the preheating parameter and the constant temperature parameter, wherein the method comprises the following steps:
Judging whether the solder impurity elimination parameter meets the requirement of a threshold impurity elimination parameter, if so, not optimizing the preheating parameter and the constant temperature parameter, and if not, calculating to obtain impurity elimination parameter deviation;
correcting the preset step length according to the impurity elimination parameter deviation to obtain a preparation optimization step length;
and constructing a preparation optimization function for optimizing the preheating parameter and the constant temperature parameter, wherein the preparation optimization function comprises the following formula:
；
wherein PF is the preparation fitness, In order to optimize the impurity elimination parameters after the preheating parameters and the constant temperature parameters,Is a threshold impurity elimination parameter;
adopting a preparation optimization step length to adjust the preheating parameter and the constant temperature parameter to obtain a first preheating parameter and a first constant temperature parameter;
Adopting the first preheating parameter and the first constant temperature parameter, combining the solder parameter and spot material specification information, carrying out solder impurity elimination prediction to obtain a first impurity elimination parameter, and calculating to obtain a first preparation fitness;
Judging whether the first impurity elimination parameter is larger than the solder impurity elimination parameter, if so, reducing the preparation optimization step length, if not, amplifying the preparation optimization step length, adjusting the first preheating parameter and the first constant temperature parameter to obtain a second preheating parameter and a second constant temperature parameter, and predicting to obtain a second impurity elimination parameter and a second preparation fitness;
judging according to the second preparation fitness and the first preparation fitness to obtain an optimization basis;
continuously optimizing and updating to convergence based on the optimization basis, and outputting final optimal preheating parameters and optimal constant temperature parameters;
When the reflow paving parameter does not meet the requirement of a preset threshold reflow paving parameter, calculating reflow paving parameter deviation, setting a reflow optimization step length, optimizing the reflow parameter to obtain an optimal reflow parameter, and comprising the following steps:
judging whether the reflow paving parameters meet the requirements of threshold reflow paving parameters, if so, not optimizing the reflow parameters, and if not, calculating to obtain reflow paving parameter deviation;
correcting a preset step length according to the reflow paving parameter deviation to obtain a reflow optimization step length;
Constructing a reflux optimization function for optimizing reflux parameters, wherein the reflux optimization function comprises the following formula:
；
wherein HF is reflux fitness, To optimize the reflow flattening parameters after the reflow parameters,Paving parameters for threshold reflux;
and optimizing the reflow parameters according to the reflow optimization step length and the reflow optimization function to obtain the optimal reflow parameters.
2. The method for adaptively optimizing reflow process parameters of claim 1, wherein collecting solder parameters for reflow and collecting spot-size images of solder spot-size, identifying spot-size specification information, comprises:
Detecting solder components for reflow soldering to obtain solder parameters, wherein the solder components comprise alloy, soldering flux and solvent;
collecting a spot material image after solder spot material on a target circuit board;
collecting a sample spot-material image set according to the data record of the circuit board reflow soldering, marking spot-material specifications, obtaining a sample spot-material specification information set, and training a spot-material specification identifier;
and identifying the spot material image by adopting the spot material specification identifier to obtain spot material specification information.
3. The method for adaptively optimizing parameters of a reflow process according to claim 1, wherein collecting preheating parameters and constant temperature parameters in a current reflow process, and performing solder impurity elimination prediction in combination with the solder parameters and spot-size specification information, comprises:
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 preheating and constant temperature stage data under different preheating parameters, constant temperature parameters, solder parameters and spot material specification information;
And taking the sample solder parameter set, the sample spot material specification information set, the sample preheating parameter set and the sample constant temperature parameter set as inputs, taking the sample solder impurity elimination parameter set as outputs, training an impurity elimination predictor, and carrying out solder impurity elimination prediction on the preheating parameter, the constant temperature parameter, the solder parameter and the spot material specification information to obtain solder impurity elimination parameters.
4. The method of claim 1, wherein determining according to the second readiness-to-fit degree and the first readiness-to-fit degree to obtain an optimization basis comprises:
When the second preparation fitness is larger than the first preparation fitness, taking the second preheating parameter and the second constant temperature parameter as optimization bases;
and when the second preparation fitness is not greater than the first preparation fitness, calculating the adjacency of the second impurity elimination parameter and the first impurity elimination parameter, and when the adjacency is greater than a preset adjacency threshold, taking the second preheating parameter and the second constant temperature parameter as optimization bases, otherwise, taking the first preheating parameter and the first constant temperature parameter as optimization bases.
5. The method for adaptively optimizing reflow process parameters according to claim 1, wherein collecting reflow parameters in a current reflow process, and performing solder reflow paving prediction in combination with the optimal impurity removal parameters to obtain reflow paving parameters, comprises:
Collecting a sample reflow parameter set and a sample impurity elimination parameter set according to processing data records of a reflow stage of reflow soldering, and collecting a sample reflow paving parameter set, wherein the sample reflow paving parameter comprises a paving uniformity parameter of a solder joint after reflow;
Training a reflow paving predictor by adopting the sample reflow parameter set, the sample impurity eliminating parameter set and the sample reflow paving parameter set, and carrying out solder reflow paving prediction on the reflow parameters and the optimal impurity eliminating parameters to obtain reflow paving parameters.
6. The method of claim 1, wherein optimizing reflow parameters according to the reflow optimization steps and the reflow optimization function comprises:
adopting the reflux optimization step length to adjust the reflux parameter to obtain a first reflux parameter;
Adopting the first reflow parameters, combining the optimal impurity elimination parameters, carrying out reflow paving prediction to obtain first reflow paving parameters, and calculating to obtain first reflow fitness;
Judging whether the first reflow paving parameter is larger than the reflow paving parameter, if so, reducing the reflow optimization step length, if not, amplifying the reflow optimization step length, adjusting the first reflow parameter to obtain a second reflow parameter, and predicting to obtain a second reflow paving parameter and a second reflow fitness;
and judging according to the second reflux fitness and the first reflux fitness to obtain an optimization basis, optimizing until convergence, and outputting a final optimal reflux parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410885439.0A CN118428244B (en) | 2024-07-03 | 2024-07-03 | Reflow soldering process parameter self-adaptive optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410885439.0A CN118428244B (en) | 2024-07-03 | 2024-07-03 | Reflow soldering process parameter self-adaptive optimization method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118428244A CN118428244A (en) | 2024-08-02 |
| CN118428244B true CN118428244B (en) | 2024-11-19 |
Family
ID=92335651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410885439.0A Active CN118428244B (en) | 2024-07-03 | 2024-07-03 | Reflow soldering process parameter self-adaptive optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118428244B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119407391B (en) * | 2024-12-20 | 2025-07-15 | 江苏银羊不锈钢管业有限公司 | Welding deformation optimizing system for stainless steel pipes |
| CN119785946B (en) * | 2025-03-10 | 2025-06-10 | 飞琳科新材料(南通)有限公司 | Aviation drag reduction film self-cleaning performance optimization method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114218703A (en) * | 2021-12-13 | 2022-03-22 | 深圳市浦联智能科技有限公司 | Method, Apparatus and Equipment for Reflow Soldering Process Parameter Optimization Based on Machine Learning |
| CN116679616A (en) * | 2023-05-27 | 2023-09-01 | 深圳一道创新技术有限公司 | Reflow soldering process parameter control method, device, equipment and medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6352192B1 (en) * | 2000-02-29 | 2002-03-05 | Motorola, Inc. | System and method to control solder reflow furnace with wafer surface characterization |
| CN116050249A (en) * | 2022-12-09 | 2023-05-02 | 中国电子科技集团公司第三十八研究所 | Reflow soldering spot morphology prediction method |
-
2024
- 2024-07-03 CN CN202410885439.0A patent/CN118428244B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114218703A (en) * | 2021-12-13 | 2022-03-22 | 深圳市浦联智能科技有限公司 | Method, Apparatus and Equipment for Reflow Soldering Process Parameter Optimization Based on Machine Learning |
| CN116679616A (en) * | 2023-05-27 | 2023-09-01 | 深圳一道创新技术有限公司 | Reflow soldering process parameter control method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118428244A (en) | 2024-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118428244B (en) | Reflow soldering process parameter self-adaptive optimization method | |
| CN106881462B (en) | A kind of on-line checking and optimization system for selective laser fusing forming defects | |
| CN111899241B (en) | Quantitative on-line detection method and system for defects of PCB (printed Circuit Board) patches in front of furnace | |
| CN112362679B (en) | Image recognition device, image recognition method and computer program product thereof | |
| CN111757014B (en) | Focal length adjusting method, device, equipment and storage medium of network camera | |
| TWI761806B (en) | Image recognition apparatus, image recognition method, and computer program product thereof | |
| CN114971433B (en) | Quality control method, device, equipment and storage medium based on industrial internet | |
| US20220314552A1 (en) | Additive manufacturing system and method and feature extraction method | |
| CN112304952B (en) | Image recognition device, image recognition method and computer program product thereof | |
| CN117970595B (en) | Microscope automatic focusing method based on deep learning and image processing | |
| CN113747041A (en) | Camera focusing method and focusing method based on recurrent neural network | |
| CN114723706A (en) | Welding spot detection and positioning method based on machine vision | |
| CN115880302A (en) | Instrument panel welding quality detection method based on image analysis | |
| CN115810133A (en) | Welding control method based on image processing and point cloud processing and related equipment | |
| CN116822342A (en) | Process identification and performance prediction method for zirconium alloy laser cutting | |
| CN115775249A (en) | A method, system, and storage medium for monitoring the forming quality of additively manufactured parts | |
| CN119358413B (en) | Plate making optimization method for screen printing | |
| CN113378663B (en) | Inspection pointer type circular instrument identification method and device | |
| WO2021109050A1 (en) | Smt solder joint quality control method and system based on particle swarm optimization | |
| CN119368874A (en) | A method and system for adjusting wire feeding speed of wire feeder | |
| CN119151928A (en) | Defect detection method, device, equipment and medium based on few sample learning | |
| US12106465B2 (en) | Image annotation method, device and system | |
| SE526624C2 (en) | Evaluation of welding quality | |
| CN114697548B (en) | Microscopic image shooting focusing method and device | |
| CN115330761A (en) | Surface printing displacement defect identification method for electronic product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |