CN116423005A - Tin soldering process optimization method and system for improving welding precision - Google Patents
Tin soldering process optimization method and system for improving welding precision Download PDFInfo
- Publication number
- CN116423005A CN116423005A CN202310702488.1A CN202310702488A CN116423005A CN 116423005 A CN116423005 A CN 116423005A CN 202310702488 A CN202310702488 A CN 202310702488A CN 116423005 A CN116423005 A CN 116423005A
- Authority
- CN
- China
- Prior art keywords
- welding
- feedback
- result
- characteristic
- information
- 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.)
- Granted
Links
- 238000003466 welding Methods 0.000 title claims abstract description 242
- 238000000034 method Methods 0.000 title claims abstract description 98
- 238000005476 soldering Methods 0.000 title claims abstract description 40
- 238000005457 optimization Methods 0.000 title claims abstract description 37
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 title abstract description 11
- 238000012544 monitoring process Methods 0.000 claims abstract description 77
- 230000008569 process Effects 0.000 claims abstract description 51
- 230000002159 abnormal effect Effects 0.000 claims description 37
- 230000011218 segmentation Effects 0.000 claims description 26
- 238000004220 aggregation Methods 0.000 claims description 14
- 230000002776 aggregation Effects 0.000 claims description 14
- 238000009826 distribution Methods 0.000 claims description 14
- 238000011156 evaluation Methods 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 12
- 230000006978 adaptation Effects 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 229910000679 solder Inorganic materials 0.000 abstract description 4
- 230000000694 effects Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
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
- B23K3/00—Tools, devices, or special appurtenances for soldering, e.g. brazing, or unsoldering, not specially adapted for particular methods
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention provides a tin soldering process optimization method and a tin soldering process optimization system for improving welding precision, which relate to the technical field of process optimization, and are used for collecting basic information of a welding piece, wherein the basic information comprises basic attribute information and basic position information, carrying out initial positioning image collection, constructing an initial information set of a welding position, matching a welding scheme, generating fitting node monitoring characteristics, generating feedback monitoring nodes, carrying out feedback monitoring image collection, identifying and obtaining feedback characteristics, carrying out characteristic deviation comparison on the feedback characteristics, and carrying out welding control according to a feedback control scheme matched with the comparison result. The invention solves the technical problems of welding quality fluctuation and low production efficiency caused by factors such as manual operation, equipment precision, solder quality and the like in the traditional soldering process.
Description
Technical Field
The invention relates to the technical field of process optimization, in particular to a tin soldering process optimization method and a tin soldering process optimization system for improving welding precision.
Background
In the field of electronic manufacturing, a soldering process is a common soldering method, and is mainly used for connecting electronic components and circuit boards, and along with the increasing miniaturization, high density and high performance of electronic products, the requirements on the precision and stability of the soldering process are higher and higher. The traditional soldering process is limited by factors such as manual operation, equipment precision, solder quality and the like, and is easy to cause fluctuation of the welding quality and low in production efficiency, so that research on a soldering process optimization method for improving the welding precision has important practical significance.
Disclosure of Invention
The embodiment of the application provides a tin soldering process optimization method and a tin soldering process optimization system for improving welding precision, which are used for solving the technical problems of fluctuation of welding quality and low production efficiency caused by factors such as manual operation, equipment precision, solder quality and the like in the traditional tin soldering process.
In view of the above problems, embodiments of the present application provide a method and a system for optimizing a soldering process for improving soldering accuracy.
In a first aspect, an embodiment of the present application provides a method for optimizing a soldering process for improving welding accuracy, where the method includes: basic information acquisition is carried out on the welding piece, wherein the basic information comprises basic attribute information and basic position information; the welding piece is subjected to initial positioning image acquisition based on the basic information, and an initial information set of a welding position is constructed; matching a welding scheme based on the initial information set and the basic information, and generating fitting node monitoring characteristics; based on the fitting node monitoring characteristics, generating feedback monitoring nodes, performing image acquisition of feedback monitoring, and identifying and obtaining feedback characteristics; performing feature deviation comparison on the feedback features through the fit node monitoring features, and matching a feedback control scheme according to the comparison result; and performing welding control on the welding piece through the feedback control scheme.
In a second aspect, embodiments of the present application provide a soldering process optimization system for improving soldering accuracy, the system comprising: the base information acquisition module is used for acquiring base information of the welding piece, wherein the base information comprises base attribute information and base position information; the initial information construction module is used for carrying out initial positioning image acquisition on the welding piece based on the basic information and constructing an initial information set of a welding position; the welding scheme matching module is used for matching a welding scheme based on the initial information set and the basic information and generating fitting node monitoring characteristics; the feedback characteristic acquisition module is used for generating a feedback monitoring node based on the fitting node monitoring characteristic, executing image acquisition of feedback monitoring and identifying and acquiring the feedback characteristic; the characteristic deviation comparison module is used for comparing the characteristic deviation of the feedback characteristic through the fitting node monitoring characteristic and matching a feedback control scheme according to the comparison result; and the welding control module is used for controlling the welding of the welding piece through the feedback control scheme.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
the method comprises the steps of collecting basic information of a welding part, wherein the basic information comprises basic attribute information and basic position information, collecting an image of initial positioning, constructing an initial information set of a welding position, matching a welding scheme, generating a fitting node monitoring characteristic, generating a feedback monitoring node, executing the image collection of feedback monitoring, identifying and obtaining a feedback characteristic, comparing the characteristic deviation of the feedback characteristic, matching a feedback control scheme according to the comparison result, and performing welding control through the feedback control scheme. The automatic adjustment of the welding process is realized, and then the welding equipment and the technological process are optimized, so that the technical effects of reducing manual intervention, improving welding quality and improving production efficiency are achieved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
Fig. 1 is a schematic flow diagram of a soldering process optimization method for improving soldering accuracy according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a feature optimization result-based matching feedback control scheme in a soldering process optimization method for improving soldering accuracy according to an embodiment of the present application;
fig. 3 is a schematic flow chart of generating an initial information set in a soldering process optimization method for improving the welding precision according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a soldering process optimizing system for improving the welding precision according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a basic information acquisition module 10, an initial information construction module 20, a welding scheme matching module 30, a feedback characteristic acquisition module 40, a characteristic deviation comparison module 50 and a welding control module 60.
Detailed Description
The embodiment of the application provides a tin soldering process optimization method for improving the welding precision, which is used for solving the technical problems of welding quality fluctuation and low production efficiency caused by factors such as manual operation, equipment precision, solder quality and the like in the traditional tin soldering process.
Example 1
As shown in fig. 1, an embodiment of the present application provides a method for optimizing a soldering process for improving soldering precision, where the method includes:
step S100: basic information acquisition is carried out on the welding piece, wherein the basic information comprises basic attribute information and basic position information;
specifically, basic attribute information of the welding piece is collected, including the type, material, size, shape and the like of the welding piece, and the information is used for determining a welding method and technological parameters applicable to the welding piece; the dimensions and positions of the weldment are measured to obtain basic positional information, including the absolute and relative positions of the weldment, and the position and length of the weld joint, for accurate positioning and welding in the next steps. By the method, basic information of the welding piece is collected in detail, and important data support is provided for the optimization of the subsequent soldering process.
Step S200: the welding piece is subjected to initial positioning image acquisition based on the basic information, and an initial information set of a welding position is constructed;
specifically, the camera and the light source are correctly arranged to ensure that the position, angle and focal length of the camera are matched with those of the welding piece so as to capture clear images, and the light source is sufficiently and uniformly distributed to reduce the influence of shadows and light reflection. Capturing an initial positioning image of the welding piece by using the camera, and acquiring an initial positioning image acquisition result.
Further, as shown in fig. 3, step S200 of the present application further includes:
step S210: constructing an identification main body feature set of the welding piece according to the basic information;
step S220: extracting color features of the main body recognition feature set to generate color distribution features;
step S230: performing main body recognition through an image acquisition result of initial positioning by continuous constraint of the color distribution characteristics and the color positions;
step S240: and generating the initial information set according to the main body identification result.
Specifically, a set of body features including shape, size, texture, etc. is constructed from the resulting base information, and the body feature set is identified for use in subsequent image identification and localization processes.
Preprocessing the acquired welding piece image, including denoising, brightness adjustment and the like. In a color space of RGB or the like, a color histogram describing the distribution of colors in an image is calculated for the preprocessed image. And calculating color moments for the preprocessed image, wherein the color moments are features describing color distribution, color difference and color complexity of the image and comprise a first-order color moment, namely a mean value, a second-order color moment, namely a variance and a third-order color moment, namely a skewness. And integrating the extracted color histogram features and the color moment features to generate color distribution features.
And (3) image segmentation is carried out on the image acquisition result of the initial positioning according to the generated color distribution characteristics, wherein the segmentation method comprises a threshold value method, a clustering method and the like. Based on image segmentation, the segmentation result is further optimized by applying continuous constraint of color positions, the continuous constraint of the color positions is used for removing noise and misjudging segmentation areas, accuracy of main body recognition is improved, and the main body part of the welding piece is recognized by combining the image segmentation result and the continuous constraint of the color positions.
And extracting key information such as welding positions, sizes, shapes and the like from the main body recognition result, integrating the extracted main body information with basic information to form a complete initial information set for subsequent welding scheme matching and fitting node monitoring feature generation.
Further, step S230 of the present application further includes:
step S231: performing gray level conversion on the image acquisition result, and determining a gray level starting point;
step S232: watershed segmentation is carried out on the gray image through the gray starting point, and an initial segmentation result is generated;
step S233: performing image aggregation constraint of the image acquisition result through continuous constraint of the color distribution characteristics and the color positions;
step S234: mapping the image aggregation constraint to the gray level image, and canceling the abnormal watershed of the initial segmentation result according to the image aggregation constraint;
step S235: and carrying out the main body recognition according to the adjusted segmentation result.
Specifically, the collected color image is converted into a gray image, wherein the gray image is an image only containing brightness information, and the brightness of a black-and-white image is represented by one pixel value, so that the image information is simplified, and the calculation complexity is reduced. And selecting a representative gray value in the gray image as a gray starting point, e.g., a peak or a valley in the histogram, based on the image histogram, the gray starting point being used as an input parameter for a subsequent watershed segmentation algorithm.
And calculating a gradient image of the gray level image by weighting differences of gray level values in the upper, lower, left and right fields of each pixel in the image, wherein the gradient image represents the change rate of the pixel values in the image and is used for describing the edge and texture information of the image. The gradient image is segmented by using a watershed algorithm, wherein the watershed algorithm is an area segmentation method based on image gradients, the image is regarded as a terrain, gradient values are regarded as the height of the terrain, and the watershed segmentation process is similar to finding a watershed line in the terrain and dividing the terrain into different areas. And generating an initial segmentation result according to the segmentation result obtained by the watershed algorithm, wherein the initial segmentation result is used as a basis for carrying out main body recognition in the subsequent step.
And calculating the color similarity between pixel points in the image according to the color distribution characteristics so as to evaluate whether the pixel points belong to the same main body. A continuous constraint of color positions is defined according to the spatial adjacency and the color gradient, so that pixels with similar colors are further screened, and the selected pixels with similar colors are ensured to be continuous in space and smooth in color change. And combining the color similarity with continuous constraint conditions to obtain image aggregation constraints, wherein the constraints are used for correcting the watershed segmentation result to avoid over segmentation or under segmentation.
The image aggregation constraint is applied to the gray scale image, and abnormal watershed, such as over-segmentation or under-segmentation, in the initial segmentation result is eliminated according to the image aggregation constraint. Extracting each segmented region from the adjusted segmented result, matching the segmented region with the predefined main body features of the welding piece by adopting methods such as template matching, feature point matching and the like, and identifying the main body part of the welding piece in the image according to the feature matching result.
Step S300: matching a welding scheme based on the initial information set and the basic information, and generating fitting node monitoring characteristics;
specifically, based on the collected basic information and initial information set, the welding requirements and difficulties of the weldment are analyzed, for example, for thicker metal weldments, higher welding temperatures and greater welding currents are required; for complex shaped weldments, more precise weld position control is required. According to the analysis result, selecting a proper welding scheme from a preset welding scheme library, wherein the schemes in the welding scheme library comprise different welding methods, welding parameters and welding sequences, wherein the welding methods are TIG welding, MIG welding and the like, and the welding parameters are current, voltage, welding speed and the like. The matched welding scheme can meet the welding requirement of the welding piece, and meanwhile, the welding process is optimized to a certain extent.
After matching to a suitable welding scheme, key nodes in the welding process are monitored, wherein the key nodes comprise weld joint positions, welding temperatures, welding speeds and the like, and fitting node monitoring features are generated according to the key nodes, and the fitting node monitoring features comprise image features, sensor data and the like and are used for subsequent real-time monitoring and control.
Step S400: based on the fitting node monitoring characteristics, generating feedback monitoring nodes, performing image acquisition of feedback monitoring, and identifying and obtaining feedback characteristics;
specifically, feedback monitoring nodes are set according to the fit node monitoring characteristics, and the nodes comprise key parameters such as weld joint positions, welding temperatures, welding speeds and the like, so that the welding process is monitored in real time. In the welding process, a camera or other image acquisition equipment is used for carrying out real-time image acquisition on the feedback monitoring node, so that clear and non-shielding images are ensured, and the information of the key node can be captured. The acquired images are processed and identified, including image denoising, edge detection, shape identification, feature extraction and the like, feedback features of key parameters are extracted, and key parameter information in the welding process is obtained in real time through image processing and identification. And generating feedback characteristics according to the image processing and recognition results, wherein the feedback characteristics are used for subsequent characteristic deviation comparison and matching of a feedback control scheme so as to adjust the welding process in real time and improve the welding precision.
Step S500: performing feature deviation comparison on the feedback features through the fit node monitoring features, and matching a feedback control scheme according to the comparison result;
further, as shown in fig. 2, step S500 of the present application further includes:
step S510: performing characteristic position association on the fitting node monitoring characteristics to generate characteristic position association values;
step S520: when the characteristic deviation comparison is carried out on the feedback characteristic through the fitting node monitoring characteristic, firstly, carrying out deviation judgment of the characteristic comparison;
step S530: if the deviation judging result exceeds a preset deviation threshold value, performing influence evaluation of the associated node according to the characteristic position associated value and the deviation judging result;
step S540: and carrying out feature optimization of the monitoring features of the fitting nodes according to the influence evaluation result, and matching a feedback control scheme based on the feature optimization result.
Specifically, the position information of the feature, such as the coordinates of the feature points, the bounding box of the region, and the like, is extracted from the fitting node monitoring feature and the feedback feature. The Euclidean distance is adopted, the feature and the feedback feature are monitored aiming at each pair of fitting nodes, the spatial distance between the feature and the feedback feature is calculated, the feature position correlation value is calculated according to the spatial distance value, different measurement modes such as similarity measurement, correlation measurement and the like can be adopted for the correlation value, and the higher correlation value indicates that the spatial relationship between the two groups of features is similar.
And calculating the difference between the monitoring characteristic and the feedback characteristic of the fitting node, for example, calculating by adopting Euclidean distance, and setting a proper deviation threshold according to the requirement of the actual welding process and the tolerance to the precision, wherein the deviation threshold is used for judging whether the characteristic difference exceeds an acceptable range. Comparing the calculated characteristic difference with a set deviation threshold, and if the characteristic difference exceeds the deviation threshold, indicating that a larger deviation exists between the monitoring characteristic and the feedback characteristic of the fitting node, wherein characteristic optimization is required; otherwise, the difference between the two sets of features may be considered to be within acceptable limits, without feature optimization.
And determining associated nodes related to the current welding position according to the characteristic position associated values, wherein the associated nodes refer to other nodes related to the current welding position, and the associated nodes can have influence on welding precision, such as adjacent welding nodes, other nodes on the same welding path or nodes with similar characteristics. And for each association node, calculating the association degree of each association node with the current welding position according to the feature similarity. And taking the association degree as a weight, and carrying out weighted average on the deviation judgment results of all the association nodes, so as to evaluate the influence of the association nodes and obtain a comprehensive influence evaluation value.
And according to the influence evaluation result, preferentially selecting the associated node with higher influence evaluation value for optimization, and determining the fitting node monitoring characteristics needing to be optimized. Feature optimization is performed, for example, by weighted averaging the features of the associated nodes to reduce the impact of outlier features. In the optimization process, the optimized characteristics still meet the requirements of the welding process, such as stability, reliability and the like. Based on the optimized characteristics, and referring to the historical data, a proper feedback control scheme is matched, including parameters such as welding speed, welding temperature, welding pressure and the like, so as to improve welding precision.
Further, step S500 of the present application further includes:
step S550: when the influence evaluation result is that the associated feature adjustment is needed, the corresponding feedback feature is used as a basic feature;
step S560: taking the matched feedback control scheme as a control scheme, and performing welding fitting of the positions of the associated nodes;
step S570: generating compensation fitting node monitoring characteristics of the associated nodes, and replacing the fitting node monitoring characteristics of the associated nodes through the compensation fitting node monitoring characteristics;
step S580: and performing subsequent feedback control execution according to the replacement result.
Specifically, when the impact evaluation result shows that the relevant characteristics need to be adjusted, the feedback characteristics are regarded as basic characteristics for subsequent operation, which means that the welding process is optimized according to the welding quality condition fed back in real time.
The matched feedback control scheme is analyzed to learn parameter adjustment suggestions, such as welding speed, welding temperature, welding pressure and the like, contained in the feedback control scheme. The welding parameters associated with the node locations are adjusted according to the feedback control scheme recommendation, e.g., if the feedback control scheme suggests an increase in welding speed, the speed setting of the welding device is adjusted accordingly. And performing welding fitting at the relevant node positions, performing welding operation according to the adjusted welding parameters, continuously monitoring welding quality in the welding fitting process, and collecting welding process data in real time by means of image acquisition equipment, sensors and the like. And according to the monitored welding quality data, evaluating welding fitting results of the associated node positions, including evaluating factors such as weld joint shape, welding strength and the like.
And analyzing the performance of the joint according to the welding fitting result of the joint position, identifying welding parameters or conditions still needing to be optimized, and generating corresponding compensation fitting joint monitoring characteristics according to the analysis result so as to make up for the defects of the original fitting joint monitoring characteristics. And replacing the original fitting node monitoring characteristics with the generated compensating fitting node monitoring characteristics, so that welding quality evaluation and parameter adjustment are carried out by using the updated fitting node monitoring characteristics in the follow-up feedback control execution process.
And updating the control strategy of the welding process according to the replaced fitting node monitoring characteristics to realize more accurate welding quality control, executing subsequent feedback control operations, such as adjusting welding parameters, modifying the welding process or conditions and the like, continuously monitoring and evaluating the welding quality in the process of executing the feedback control to ensure that the welding process is always in an optimal state, and continuing to update the fitting node monitoring characteristics and execute the feedback control until the welding quality reaches an expected target if the welding quality still has room for improvement.
Step S600: and performing welding control on the welding piece through the feedback control scheme.
Specifically, according to the determined feedback control scheme, the welding equipment is correspondingly adjusted, including parameters such as welding current, voltage, welding speed and the like, and the welding pieces are connected according to the parameters, so that the welding control of the welding pieces is completed.
Further, the present application further includes:
step S710: judging whether the characteristic deviation comparison result meets an early warning threshold value or not;
step S720: when the characteristic deviation comparison result meets the early warning threshold value, a shutdown control instruction is generated;
step S730: and stopping welding the welding piece through the stop control instruction, and performing abnormal welding early warning.
Specifically, based on previous empirical data or understanding of the welding process, an early warning threshold is preset, and the early warning threshold is selected to ensure that the feature deviation comparison result does not trigger early warning under normal welding conditions, so as to determine whether the feature deviation exceeds a normal range. And comparing the characteristic deviation comparison result with the early warning threshold value, if the characteristic deviation comparison result exceeds the early warning threshold value, considering that the welding process is abnormal, otherwise, if the characteristic deviation comparison result is lower than the early warning threshold value, considering that the welding process is normal.
If the characteristic deviation comparison result exceeds a preset early warning threshold value, poor welding or welding failure can be caused, so that measures are needed to avoid continuous welding in time, and a shutdown control command is generated by the system at the moment so as to pause and check the welding process.
And according to the generated shutdown control instruction, suspending welding of the welding equipment to the welding piece, and simultaneously, sending out abnormal welding early warning by the system, informing an operator or related responsible persons so as to carry out problem investigation and solution, such as checking the welding equipment, welding parameters, welding materials, welding process and the like, so as to find out the reason for causing the welding quality deviation. Once the problem is resolved, the welding process may be resumed and the weld quality monitored and controlled again, and during the subsequent welding process, the system continues to perform the foregoing steps to ensure that the weld quality is always within acceptable limits.
Further, the present application further includes:
step S810: performing abnormal acquisition of welding control according to the feedback characteristics and the welding scheme;
step S820: generating an adaptation association coefficient based on the abnormal acquisition result;
step S830: and carrying out mapping association on the abnormal acquisition result and the welding piece through the adaptation association coefficient, and carrying out matching optimization of a subsequent welding scheme according to the mapping association result.
Specifically, in the welding process, feedback information such as parameters of welding temperature, welding speed, weld width and the like are collected in real time through equipment such as a sensor and the like, meanwhile, image information of the welding process is collected, analysis is carried out based on the collected feedback information and the image information, abnormal conditions such as problems of welding defects, temperature deviation and the like in the welding process are detected, and after the abnormal conditions are found, corresponding abnormal information including abnormal images, abnormal parameters and the like is collected.
And analyzing the abnormal reasons according to the abnormal acquisition results, and determining welding parameters needing to generate the adaptive correlation coefficients, wherein in a soldering process, the abnormal conditions can be caused by factors such as temperature, welding time and the like, so that the welding parameters needing to generate the adaptive correlation coefficients are determined to be the temperature, the welding time and the like. And determining a data set required for generating the adaptation association coefficient according to the feedback characteristic and the welding scheme so as to generate the adaptation association coefficient according to an abnormal acquisition result. By training the abnormal data, a model adapting the association coefficient is generated, new abnormal data is predicted according to the model, and accordingly the adaptation association coefficient is generated, and the adaptation association coefficient is used for describing the relation between the abnormal data and ideal data.
Mapping the abnormal data to the welding piece, determining the position and the influence range corresponding to the abnormal data, namely, the area where the abnormal data is located, mapping the area on the welding piece to the welding scheme, and determining the welding scheme area corresponding to the area where the abnormal data is located. And carrying out matching optimization on a subsequent welding scheme according to the matching association coefficient and the welding scheme area corresponding to the area where the abnormal data are located, wherein the matching optimization comprises the steps of increasing the number of welding points, adjusting welding parameters and the like, so that the welding efficiency is improved and the occurrence of welding abnormality is reduced on the premise of ensuring the welding quality.
In summary, the method and the system for optimizing the soldering process for improving the welding precision provided by the embodiment of the application have the following technical effects:
the method comprises the steps of collecting basic information of a welding part, wherein the basic information comprises basic attribute information and basic position information, collecting an image of initial positioning, constructing an initial information set of a welding position, matching a welding scheme, generating a fitting node monitoring characteristic, generating a feedback monitoring node, executing the image collection of feedback monitoring, identifying and obtaining a feedback characteristic, comparing the characteristic deviation of the feedback characteristic, matching a feedback control scheme according to the comparison result, and performing welding control through the feedback control scheme.
The automatic adjustment of the welding process is realized, and then the welding equipment and the technological process are optimized, so that the technical effects of reducing manual intervention, improving welding quality and improving production efficiency are achieved.
Example two
Based on the same inventive concept as a soldering process optimizing method for improving the welding precision in the foregoing embodiments, as shown in fig. 4, the present application provides a soldering process optimizing system for improving the welding precision, the system comprising:
the base information acquisition module 10 is used for acquiring base information of the welding piece, wherein the base information comprises base attribute information and base position information;
the initial information construction module 20 is used for carrying out initial positioning image acquisition on the welding piece based on the basic information, and constructing an initial information set of a welding position;
a welding scheme matching module 30, wherein the welding scheme matching module 30 is configured to match a welding scheme based on the initial information set and the basic information, and generate a fit node monitoring feature;
the feedback feature acquisition module 40 is configured to generate a feedback monitoring node based on the fitted node monitoring feature, perform image acquisition of feedback monitoring, and identify and obtain a feedback feature;
the feature deviation comparison module 50 is used for comparing the feature deviation of the feedback feature through the fit node monitoring feature, and matching a feedback control scheme according to the comparison result;
a welding control module 60, wherein the welding control module 60 is used for performing welding control of the welding piece through the feedback control scheme.
Further, the system further comprises:
the characteristic position association module is used for carrying out characteristic position association on the fitting node monitoring characteristics and generating characteristic position association values;
the deviation judging module is used for firstly carrying out deviation judgment of feature comparison when the feature deviation comparison is carried out on the feedback features through the fitting node monitoring features;
the influence evaluation module is used for evaluating the influence of the associated node according to the characteristic position associated value and the deviation judgment result if the deviation judgment result exceeds a preset deviation threshold value;
and the characteristic optimization module is used for carrying out characteristic optimization of the monitoring characteristics of the fitting node according to the influence evaluation result and matching a feedback control scheme based on the characteristic optimization result.
Further, the system further comprises:
the basic feature acquisition module is used for taking the corresponding feedback feature as a basic feature when the influence evaluation result is that the associated feature adjustment is needed;
the welding fitting module is used for taking the matched feedback control scheme as a control scheme and performing welding fitting of the associated node positions;
the characteristic replacement module is used for generating compensation fitting node monitoring characteristics of the associated nodes, and replacing the fitting node monitoring characteristics of the associated nodes through the compensation fitting node monitoring characteristics;
and the feedback control execution module is used for executing subsequent feedback control according to the replacement result.
The identifying main body feature construction module is used for constructing an identifying main body feature set of the welding piece according to the basic information;
the color feature extraction module is used for extracting color features of the main body identification feature set and generating color distribution features;
the main body identification module is used for carrying out main body identification through the image acquisition result of initial positioning by the continuous constraint of the color distribution characteristics and the color positions;
and generating an initial information set, and generating the initial information set according to the main body identification result.
Further, the system further comprises:
the gray level conversion module is used for carrying out gray level conversion on the image acquisition result and determining a gray level starting point;
the watershed segmentation module is used for carrying out watershed segmentation on the gray image through the gray starting point to generate an initial segmentation result;
the image aggregation constraint module is used for carrying out image aggregation constraint on the image acquisition result through continuous constraint of the color distribution characteristics and the color positions;
the image aggregation constraint mapping module is used for mapping the image aggregation constraint to the gray level image, and canceling the abnormal watershed of the initial segmentation result according to the image aggregation constraint;
and the identification module is used for carrying out the main body identification according to the adjusted segmentation result.
Further, the system further comprises:
the judging module is used for judging whether the characteristic deviation comparison result meets an early warning threshold value or not;
the shutdown control instruction generation module is used for generating a shutdown control instruction when the characteristic deviation comparison result meets the early warning threshold value;
and the abnormal welding early warning module is used for controlling to stop welding the welding piece through the shutdown control instruction and carrying out abnormal welding early warning.
Further, the system further comprises:
the abnormal acquisition module is used for carrying out abnormal acquisition of welding control according to the feedback characteristics and the welding scheme;
the adaptation association coefficient generation module is used for generating adaptation association coefficients based on abnormal acquisition results;
and the matching optimization module is used for mapping and correlating the adaptation correlation coefficient, the abnormal acquisition result and the welding piece, and carrying out matching optimization of a subsequent welding scheme according to the mapping correlation result.
Through the foregoing detailed description of a method for optimizing a soldering process for improving the welding precision, those skilled in the art can clearly know a method and a system for optimizing a soldering process for improving the welding precision in this embodiment, and for the device disclosed in the embodiment, since the device corresponds to the method disclosed in the embodiment, the description is relatively simple, and relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A method of optimizing a soldering process to improve accuracy of a weld, the method comprising:
basic information acquisition is carried out on the welding piece, wherein the basic information comprises basic attribute information and basic position information;
the welding piece is subjected to initial positioning image acquisition based on the basic information, and an initial information set of a welding position is constructed;
matching a welding scheme based on the initial information set and the basic information, and generating fitting node monitoring characteristics;
based on the fitting node monitoring characteristics, generating feedback monitoring nodes, performing image acquisition of feedback monitoring, and identifying and obtaining feedback characteristics;
performing feature deviation comparison on the feedback features through the fit node monitoring features, and matching a feedback control scheme according to the comparison result;
and performing welding control on the welding piece through the feedback control scheme.
2. The method of claim 1, wherein the method further comprises:
performing characteristic position association on the fitting node monitoring characteristics to generate characteristic position association values;
when the characteristic deviation comparison is carried out on the feedback characteristic through the fitting node monitoring characteristic, firstly, carrying out deviation judgment of the characteristic comparison;
if the deviation judging result exceeds a preset deviation threshold value, performing influence evaluation of the associated node according to the characteristic position associated value and the deviation judging result;
and carrying out feature optimization of the monitoring features of the fitting nodes according to the influence evaluation result, and matching a feedback control scheme based on the feature optimization result.
3. The method of claim 2, wherein the method further comprises:
when the influence evaluation result is that the associated feature adjustment is needed, the corresponding feedback feature is used as a basic feature;
taking the matched feedback control scheme as a control scheme, and performing welding fitting of the positions of the associated nodes;
generating compensation fitting node monitoring characteristics of the associated nodes, and replacing the fitting node monitoring characteristics of the associated nodes through the compensation fitting node monitoring characteristics;
and performing subsequent feedback control execution according to the replacement result.
4. The method of claim 1, wherein the method further comprises:
constructing an identification main body feature set of the welding piece according to the basic information;
extracting color features of the main body recognition feature set to generate color distribution features;
performing main body recognition through an image acquisition result of initial positioning by continuous constraint of the color distribution characteristics and the color positions;
and generating the initial information set according to the main body identification result.
5. The method of claim 4, wherein the method further comprises:
performing gray level conversion on the image acquisition result, and determining a gray level starting point;
watershed segmentation is carried out on the gray image through the gray starting point, and an initial segmentation result is generated;
performing image aggregation constraint of the image acquisition result through continuous constraint of the color distribution characteristics and the color positions;
mapping the image aggregation constraint to the gray level image, and canceling the abnormal watershed of the initial segmentation result according to the image aggregation constraint;
and carrying out the main body recognition according to the adjusted segmentation result.
6. The method of claim 1, wherein the method further comprises:
judging whether the characteristic deviation comparison result meets an early warning threshold value or not;
when the characteristic deviation comparison result meets the early warning threshold value, a shutdown control instruction is generated;
and stopping welding the welding piece through the stop control instruction, and performing abnormal welding early warning.
7. The method of claim 1, wherein the method further comprises:
performing abnormal acquisition of welding control according to the feedback characteristics and the welding scheme;
generating an adaptation association coefficient based on the abnormal acquisition result;
and carrying out mapping association on the abnormal acquisition result and the welding piece through the adaptation association coefficient, and carrying out matching optimization of a subsequent welding scheme according to the mapping association result.
8. A soldering process optimization system for improving soldering accuracy, the system comprising:
the base information acquisition module is used for acquiring base information of the welding piece, wherein the base information comprises base attribute information and base position information;
the initial information construction module is used for carrying out initial positioning image acquisition on the welding piece based on the basic information and constructing an initial information set of a welding position;
the welding scheme matching module is used for matching a welding scheme based on the initial information set and the basic information and generating fitting node monitoring characteristics;
the feedback characteristic acquisition module is used for generating feedback monitoring nodes based on the fitting node monitoring characteristics, executing image acquisition of feedback monitoring and identifying and obtaining feedback characteristics;
the characteristic deviation comparison module is used for comparing the characteristic deviation of the feedback characteristic through the fitting node monitoring characteristic and matching a feedback control scheme according to the comparison result;
and the welding control module is used for controlling the welding of the welding piece through the feedback control scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310702488.1A CN116423005B (en) | 2023-06-14 | 2023-06-14 | Tin soldering process optimization method and system for improving welding precision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310702488.1A CN116423005B (en) | 2023-06-14 | 2023-06-14 | Tin soldering process optimization method and system for improving welding precision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116423005A true CN116423005A (en) | 2023-07-14 |
| CN116423005B CN116423005B (en) | 2023-10-31 |
Family
ID=87083679
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310702488.1A Active CN116423005B (en) | 2023-06-14 | 2023-06-14 | Tin soldering process optimization method and system for improving welding precision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116423005B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116719293A (en) * | 2023-08-04 | 2023-09-08 | 江苏甬金金属科技有限公司 | Production monitoring method and system for cold-rolled steel strip |
| CN116748729A (en) * | 2023-08-14 | 2023-09-15 | 山西海德拉太矿国际采矿刀具设备有限公司 | Coal cutter spiral roller tooth holder welding method based on multiple tests |
| CN117182391A (en) * | 2023-09-14 | 2023-12-08 | 江苏大地电缆有限公司 | Intelligent control method and system for longitudinal wrapping welding of fireproof cable |
| CN117351019A (en) * | 2023-12-06 | 2024-01-05 | 巴苏尼制造(江苏)有限公司 | Welding defect detection method |
| CN117182391B (en) * | 2023-09-14 | 2024-04-26 | 江苏大地电缆有限公司 | Intelligent control method and system for longitudinal wrapping welding of fireproof cable |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160180195A1 (en) * | 2013-09-06 | 2016-06-23 | Toyota Jidosha Kabushiki Kaisha | Augmenting Layer-Based Object Detection With Deep Convolutional Neural Networks |
| WO2017084186A1 (en) * | 2015-11-18 | 2017-05-26 | 华南理工大学 | System and method for automatic monitoring and intelligent analysis of flexible circuit board manufacturing process |
| CN107424154A (en) * | 2017-04-21 | 2017-12-01 | 成都信息工程大学 | Watershed image parallel partition method based on dynamically distributes |
| CN114905507A (en) * | 2022-04-18 | 2022-08-16 | 广州东焊智能装备有限公司 | Welding robot precision control method based on environment vision analysis |
| CN115085381A (en) * | 2022-06-30 | 2022-09-20 | 深圳蓝奥声科技有限公司 | Power utilization abnormity monitoring method, device and system |
| CN115238558A (en) * | 2022-08-05 | 2022-10-25 | 湖南大学重庆研究院 | High-precision aluminum alloy welding joint temperature field simulation prediction method |
| CN115833400A (en) * | 2023-02-07 | 2023-03-21 | 山东盛日电力集团有限公司 | Monitoring and early warning method and system for power equipment of transformer substation |
| CN115903707A (en) * | 2022-12-01 | 2023-04-04 | 苏州连讯电子有限公司 | Connecting line production optimization method and system based on station monitoring |
| CN115993807A (en) * | 2023-03-23 | 2023-04-21 | 日照鲁光电子科技有限公司 | Production monitoring optimization control method and system for silicon carbide |
| WO2023092302A1 (en) * | 2021-11-23 | 2023-06-01 | 宁德时代新能源科技股份有限公司 | Image recognition method and apparatus, and computer-readable storage medium |
-
2023
- 2023-06-14 CN CN202310702488.1A patent/CN116423005B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160180195A1 (en) * | 2013-09-06 | 2016-06-23 | Toyota Jidosha Kabushiki Kaisha | Augmenting Layer-Based Object Detection With Deep Convolutional Neural Networks |
| WO2017084186A1 (en) * | 2015-11-18 | 2017-05-26 | 华南理工大学 | System and method for automatic monitoring and intelligent analysis of flexible circuit board manufacturing process |
| CN107424154A (en) * | 2017-04-21 | 2017-12-01 | 成都信息工程大学 | Watershed image parallel partition method based on dynamically distributes |
| WO2023092302A1 (en) * | 2021-11-23 | 2023-06-01 | 宁德时代新能源科技股份有限公司 | Image recognition method and apparatus, and computer-readable storage medium |
| CN114905507A (en) * | 2022-04-18 | 2022-08-16 | 广州东焊智能装备有限公司 | Welding robot precision control method based on environment vision analysis |
| CN115085381A (en) * | 2022-06-30 | 2022-09-20 | 深圳蓝奥声科技有限公司 | Power utilization abnormity monitoring method, device and system |
| CN115238558A (en) * | 2022-08-05 | 2022-10-25 | 湖南大学重庆研究院 | High-precision aluminum alloy welding joint temperature field simulation prediction method |
| CN115903707A (en) * | 2022-12-01 | 2023-04-04 | 苏州连讯电子有限公司 | Connecting line production optimization method and system based on station monitoring |
| CN115833400A (en) * | 2023-02-07 | 2023-03-21 | 山东盛日电力集团有限公司 | Monitoring and early warning method and system for power equipment of transformer substation |
| CN115993807A (en) * | 2023-03-23 | 2023-04-21 | 日照鲁光电子科技有限公司 | Production monitoring optimization control method and system for silicon carbide |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116719293A (en) * | 2023-08-04 | 2023-09-08 | 江苏甬金金属科技有限公司 | Production monitoring method and system for cold-rolled steel strip |
| CN116719293B (en) * | 2023-08-04 | 2023-11-17 | 江苏甬金金属科技有限公司 | Production monitoring method and system for cold-rolled steel strip |
| CN116748729A (en) * | 2023-08-14 | 2023-09-15 | 山西海德拉太矿国际采矿刀具设备有限公司 | Coal cutter spiral roller tooth holder welding method based on multiple tests |
| CN116748729B (en) * | 2023-08-14 | 2023-10-24 | 山西海德拉太矿国际采矿刀具设备有限公司 | Coal cutter spiral roller tooth holder welding method based on multiple tests |
| CN117182391A (en) * | 2023-09-14 | 2023-12-08 | 江苏大地电缆有限公司 | Intelligent control method and system for longitudinal wrapping welding of fireproof cable |
| CN117182391B (en) * | 2023-09-14 | 2024-04-26 | 江苏大地电缆有限公司 | Intelligent control method and system for longitudinal wrapping welding of fireproof cable |
| CN117351019A (en) * | 2023-12-06 | 2024-01-05 | 巴苏尼制造(江苏)有限公司 | Welding defect detection method |
| CN117351019B (en) * | 2023-12-06 | 2024-01-30 | 巴苏尼制造(江苏)有限公司 | Welding defect detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116423005B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116423005B (en) | Tin soldering process optimization method and system for improving welding precision | |
| CN108637435B (en) | Three-dimensional weld tracking system and method based on vision and arc pressure sensing | |
| CN108982546B (en) | Intelligent robot gluing quality detection system and method | |
| WO2021169335A1 (en) | Visual online detection method for laser welding point of lithium battery tab | |
| CN109035204B (en) | Real-time detection method for weld joint target | |
| CN113324864B (en) | Pantograph carbon slide plate abrasion detection method based on deep learning target detection | |
| CN109978835B (en) | Online assembly defect identification system and method thereof | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| CN110910350A (en) | Nut loosening detection method for wind power tower cylinder | |
| CN112238292A (en) | Method for tracking space curve track of friction stir welding robot based on vision | |
| CN114407079B (en) | Method for controlling mechanical arm mounting bolt | |
| CN114119595A (en) | GMAW welding quality on-line monitoring and evaluating method based on integrated deep learning | |
| CN116563277B (en) | Machine vision-based copper-clad aluminum surface defect detection method and system | |
| CN116740044B (en) | Copper pipe milling surface processing method and system based on visual detection and control | |
| CN117232396A (en) | Visual detection system and method for product quality of high-speed production line | |
| CN116664508A (en) | Weld surface quality detection method and computer readable storage medium | |
| CN116275742A (en) | Welding method based on digital modeling and flexible weld joint recognition | |
| CN114932292A (en) | Narrow-gap passive visual weld joint tracking method and system | |
| CN115106615A (en) | Welding deviation real-time detection method and system based on intelligent working condition identification | |
| CN115569994A (en) | Automatic detection system and method for camber of plate blank | |
| CN113643352A (en) | Natural icing on-line monitoring running wire image icing degree evaluation method | |
| CN115464661B (en) | Robot control system based on digital twins | |
| CN117611676B (en) | Chip burning positioning correction method and system based on visual algorithm | |
| CN117817211A (en) | Welding automation control method and system based on machine vision | |
| CN117409332B (en) | Long wood shaving appearance data detection system and method based on big data processing |
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 |