A parameter adjustment method and device for industrial production

By monitoring the welding parameters of the welding robot, a hidden danger evaluation index is generated and intelligent adjustments are made, the quality problems caused by abnormal welding parameters are solved, ensuring the efficient operation of the welding robot and the efficient production of automobile manufacturing.

CN116890179BActive Publication Date: 2024-11-26HUSONG DIGITAL TECH (SHANGHAI) CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202311032939.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-08-16
Publication Date
2024-11-26
Estimated Expiration
2043-08-16

AI Technical Summary

Technical Problem

During the automobile manufacturing process, abnormal welding parameters of welding robots are not discovered and adjusted in time, resulting in unqualified welding quality and affecting production efficiency.

Method used

By monitoring multiple information about welding parts of the same specification by the welding robot, a hidden danger assessment index is generated, and intelligent parameter adjustments are made based on the index to prevent abnormal parameters and ensure welding quality.

Benefits of technology

Effectively prevent abnormal welding parameters, ensure efficient operation of welding robots, improve production efficiency of automobile manufacturing, and promptly notify maintenance personnel for shutdown and maintenance and analyze faults.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116890179B_ABST
    Figure CN116890179B_ABST
Patent Text Reader

Abstract

The present invention discloses a parameter adjustment method and device for industrial production, which relates to the field of intelligent welding technology for automobile manufacturing, and includes the following steps: S101, collecting multiple pieces of information when a welding robot performs intelligent welding on parts of the same specification during automobile manufacturing, including welding physical parameter information and software control information, and after collection, processing the welding physical parameter information and software control information during welding. The present invention monitors the parameters when a welding robot performs intelligent welding on parts of the same specification during automobile manufacturing. If there is an abnormal hidden danger that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time, the parameters during welding are intelligently adjusted in time, effectively preventing the welding parameters of the welding robot from being abnormal but not discovered in time, ensuring that the welding robot performs efficient welding, and further facilitating efficient production of automobile manufacturing.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent welding in automobile manufacturing, and in particular to a parameter adjustment method and device for industrial production. Background Art

[0002] Industrial welding refers to the use of various welding methods and techniques in industrial production to join parts of metal or non-metal materials together to form a permanent weld to meet specific manufacturing, construction or maintenance needs. Welding is a common metal joining technology that is widely used in various industrial fields, including automotive manufacturing, construction, aerospace, energy industry, electronic manufacturing, etc.

[0003] Automobile manufacturing involves a large number of welding tasks, including body welding, chassis welding, exhaust system welding, etc. Since automobile manufacturing involves a large amount of welding work, and welding robots can provide efficient, precise and stable welding solutions, the existing technology widely uses welding robots for intelligent welding.

[0004] When performing intelligent welding, welding robots usually make intelligent adjustments to the welding parameters. The intelligent welding system combines sensor technology, data analysis and automated control to achieve a more precise, efficient and stable welding process.

[0005] The existing technology has the following deficiencies: During the automobile manufacturing process, when a welding robot performs intelligent welding on parts of the same specification, if an abnormality occurs in the welding parameters of the welding robot but is not discovered and adjusted in time, it may result in a batch of products with unqualified welding quality, thereby inconvenience the efficient production of automobile manufacturing.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The object of the present invention is to provide a parameter adjustment method and device for industrial production. The present invention monitors the parameters of the welding robot when performing intelligent welding on parts of the same specification during the automobile manufacturing process. If there is an abnormal hidden danger that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time, the parameters during welding are intelligently adjusted in time, effectively preventing the welding parameters of the welding robot from being abnormal but not discovered in time, ensuring that the welding robot performs efficient welding, and further facilitating efficient production of automobile manufacturing, so as to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a parameter adjustment method and device for industrial production, comprising the following steps:

[0009] S101, collecting multiple pieces of information when a welding robot performs intelligent welding on parts of the same specification during automobile manufacturing, including welding physical parameter information and software control information, and after collection, processing the welding physical parameter information and software control information during welding;

[0010] S102, comprehensively analyzing the processed welding physical parameter information and software control information when the welding robot performs intelligent welding in the automobile manufacturing process to generate a hidden danger assessment index;

[0011] S103, comparing and analyzing the hidden danger assessment index generated when the welding robot performs intelligent welding in the automobile manufacturing process with a preset hidden danger assessment index reference threshold, and generating a high hidden danger risk signal and a low hidden danger risk signal;

[0012] S104. When a high hidden danger risk signal is generated when a welding robot performs intelligent welding in the automobile manufacturing process, the welding parameters are adjusted intelligently in a timely manner, and a comprehensive analysis is performed on the hidden danger assessment index output after the adjustment to generate an adjustment result signal, and different early warning prompts are issued for the adjustment result signal or no early warning prompt is issued.

[0013] Preferably, the welding physical parameter information when the welding robot performs intelligent welding on parts of the same specification in the automobile manufacturing process includes the welding current abnormal concealment coefficient and the welding speed fluctuation coefficient. After collection, the welding current abnormal concealment coefficient and the welding speed fluctuation coefficient are calibrated as αα respectively. I and β V In the automobile manufacturing process, the software control information of the welding robot for intelligent welding of parts of the same specification includes the control path deviation coefficient. After collection, the control path deviation coefficient is calibrated as γγ S .

[0014] Preferably, the logic for obtaining the welding current abnormal concealment coefficient is as follows:

[0015] A100, obtain the optimal welding current reference range when the welding robot performs intelligent welding on parts of the same specification, and calibrate the optimal welding current reference range as I min ~I max ;

[0016] A200, obtain the actual welding current value at different times during the T time when the welding robot performs intelligent welding, and calibrate the actual welding current value as I x , x represents the number of the actual welding current value at different times within T time when the welding robot performs intelligent welding, x = 1, 2, 3, 4, ..., m, m is a positive integer;

[0017] A300, compare the actual welding current value obtained within T time with the optimal welding current reference range I min ~I max Compare and set the welding current that is not in the optimal reference range I min ~I max The actual welding current value between is defined as the non-optimal current value, and the non-optimal current value is calibrated as I y , y represents the number of the non-optimal current value obtained within T time, y=1, 2, 3, 4, ..., n, n is a positive integer;

[0018] A400, calculate the welding current abnormal concealment coefficient, the calculation expression is: [t1, t2] is the period of non-optimal current value obtained within T time, t1<t2,

[0019] Preferably, the logic for obtaining the welding speed fluctuation coefficient is as follows:

[0020] B100, obtain the actual average welding rate of the welding robot for intelligent welding of parts of the same specification in different periods of time within T time, and calibrate the actual welding rate as V k , k represents the number of the actual average welding rate of different time periods within T time when the welding robot performs intelligent welding on parts of the same specification, k = 1, 2, 3, 4, ..., N, N is a positive integer;

[0021] B200. Calculate the standard deviation of the actual average welding rate at different time periods within T time when the welding robot performs intelligent welding, and calibrate the standard deviation of the actual average welding rate as R, then:

[0022]

[0023] ; Among them, V 平 The average value of the actual average welding rate at different time periods within T time when the welding robot performs intelligent welding is obtained by the calculation formula:

[0024] B300, calculate the welding speed fluctuation coefficient, the calculation expression is: ββ V =ln(R 2 +1).

[0025] Preferably, the logic for obtaining the control path deviation coefficient is as follows:

[0026] C100, obtaining an actual software-controlled welding path and a pre-planned welding path when the welding robot performs intelligent welding, and marking the actual software-controlled welding path and the pre-planned welding path as L1 and L2, respectively;

[0027] C200, dividing the actual software-controlled welding path L1 and the pre-planned welding path L2 when the welding robot performs intelligent welding into a plurality of points according to time points, and overlapping the points on the actual software-controlled welding path L1 and the points on the pre-planned welding path L2 according to time points, and then comparing and analyzing them;

[0028] C300, input the actual software controlled welding path L1 and the pre-planned welding path L2 into the two-dimensional coordinate system, use Euclidean distance calculation to calculate the distance between the points on the actual software controlled welding path L1 and the points on the pre-planned welding path L2 at the same time, and calibrate the distance between the points on the actual software controlled welding path L1 and the points on the pre-planned welding path L2 at the same time as L w , w represents the number of the actual average welding rate of different time periods within T time when the welding robot performs intelligent welding on parts of the same specification, w = 1, 2, 3, 4, ..., p, p is a positive integer;

[0029] C400, calculate the control path deviation coefficient, the calculation expression is:

[0030] Preferably, the welding current abnormal concealment coefficient αα is obtained I , welding speed fluctuation coefficient ββ V and the control path deviation coefficient γγ S Finally, a data analysis model is established based on the acquired data information to generate the hidden danger assessment index YH δ , based on the formula:

[0031]

[0032] ; Where f1, f2, and f3 are the welding current abnormal concealment coefficients αα I , welding speed fluctuation coefficient ββ V And the control path deviation coefficient is calibrated as γγ S The preset proportional coefficient, and f1, f2, and f3 are all greater than 0.

[0033] Preferably, the hidden danger assessment index generated when the welding robot performs intelligent welding in the automobile manufacturing process is compared and analyzed with a pre-set hidden danger assessment index reference threshold. If the hidden danger assessment index is greater than or equal to the hidden danger assessment index reference threshold, a high hidden danger risk signal is generated; if the hidden danger assessment index is less than the hidden danger assessment index reference threshold, a low hidden danger risk signal is generated.

[0034] Preferably, when a high hidden danger risk signal is generated during intelligent welding by a welding robot in the automobile manufacturing process, the parameters during welding are intelligently adjusted, and a data set is established for a number of hidden danger assessment indexes output after adjustment, and the data set is calibrated as P, then P = {YH δ}, δ represents the number of the hidden danger assessment index in the data set, δ = 1, 2, 3, 4, ..., u, u is a positive integer;

[0035] Calculate the mean value and standard deviation of the hidden danger assessment index in the data set, and compare the mean value and standard deviation of the hidden danger assessment index with the pre-set reference threshold of the hidden danger assessment index and the pre-set reference threshold of the standard deviation, respectively. The comparison is divided into the following cases:

[0036] If the average value of the hidden danger assessment index is greater than or equal to the reference threshold value of the hidden danger assessment index, a signal of welding parameter adjustment failure is generated and transmitted to the prompt end, and an early warning prompt of welding parameter adjustment failure is issued through the prompt end to prompt relevant staff that the welding parameter adjustment has failed and the welding robot needs to be shut down for maintenance;

[0037] If the average value of the hidden danger assessment index is less than the reference threshold value of the hidden danger assessment index and the standard deviation of the hidden danger assessment index is greater than or equal to the reference threshold value of the standard deviation, a signal indicating that the welding parameter adjustment is unstable is generated and transmitted to the prompt end, and an early warning prompt indicating that the welding parameter adjustment is unstable is issued through the prompt end, prompting relevant staff that the welding parameter adjustment is unstable and the welding robot needs to be shut down for maintenance;

[0038] If the average value of the hidden danger assessment index is less than the reference threshold value of the hidden danger assessment index and the standard deviation of the hidden danger assessment index is less than the standard deviation reference threshold value, a signal of successful welding parameter adjustment is generated and the signal is transmitted to the prompt end, and no early warning prompt is issued through the prompt end.

[0039] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0040] The present invention monitors the parameters of the welding robot when performing intelligent welding on parts of the same specification during the automobile manufacturing process. If there is an abnormal hidden danger that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time, the welding parameters are intelligently adjusted in time, effectively preventing the welding parameters of the welding robot from being abnormal but not discovered in time, ensuring that the welding robot performs efficient welding, and further facilitating efficient production of automobile manufacturing;

[0041] The present invention conducts a comprehensive analysis on the parameter adjustment of the welding robot when performing intelligent welding. If the parameter adjustment fails or the adjustment is unstable, the relevant staff will be notified in time to shut down the welding robot for maintenance to ensure that the welding robot is in an efficient welding state. Secondly, when an early warning prompt is issued, it can be understood whether the welding robot fails to adjust the parameters or the adjustment is unstable, which is convenient for maintenance personnel to reasonably analyze the possible faults of the welding robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0043] Figure 1 The present invention is a method flow chart of a parameter adjustment method and device for industrial production. DETAILED DESCRIPTION

[0044] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0045] The present invention provides Figure 1 A parameter adjustment method for industrial production shown includes the following steps:

[0046] S101, collecting multiple pieces of information when a welding robot performs intelligent welding on parts of the same specification during automobile manufacturing, including welding physical parameter information and software control information, and after collection, processing the welding physical parameter information and software control information during welding;

[0047] The welding physical parameter information when the welding robot performs intelligent welding on parts of the same specification in the automobile manufacturing process includes the welding current anomaly concealment coefficient and the welding speed fluctuation coefficient. After collection, the welding current anomaly concealment coefficient and the welding speed fluctuation coefficient are calibrated as αα I and β V ;

[0048] Abnormal current during welding may have a serious impact on the welding quality of parts. Current is one of the key parameters in the welding process, which directly affects the formation of welds, the flow of molten metal and the stability of welding quality. The following are the serious effects that abnormal current may cause:

[0049] Weak weld: If the current is too low, the flow ability of the molten metal is weakened, resulting in an incomplete weld, which may lead to insufficient weld strength and affect the reliability of the welded connection;

[0050] Porosity and slag inclusion: Abnormal current may cause the gas in the molten metal to not be effectively discharged, thus forming pores or slag inclusions in the weld, which will significantly reduce the strength and sealing of the weld;

[0051] Cold cracking: Excessive current may cause the weld area to cool too quickly, leading to cold cracking. Cold cracking may form cracks in the weld, seriously affecting the quality and strength of the weld.

[0052] Welding deformation: abnormal current may cause excessive heating of the welding area, causing welding deformation, thus affecting the size and shape of the parts;

[0053] Reduced welding strength: Improper current may cause the strength of the weld to decrease, affecting the overall performance and durability of the part;

[0054] Uneven weld: Abnormal current may cause uneven weld width and depth, affecting the consistency of welding quality;

[0055] Product quality issues: Poor welding quality may lead to product quality issues, affecting the performance, safety and reliability of the entire vehicle;

[0056] Therefore, by monitoring the welding current when the welding robot performs intelligent welding, abnormal welding current problems can be discovered in time;

[0057] The logic for obtaining the welding current abnormal concealment coefficient is as follows:

[0058] A100, obtain the optimal welding current reference range when the welding robot performs intelligent welding on parts of the same specification, and calibrate the optimal welding current reference range as I min ~I max ;

[0059] It should be noted that before actual production, conducting welding tests is an effective way to obtain the best parameters. Through the test, different welding parameter combinations can be tried to find the best welding current reference range suitable for the parts of this specification. The best welding current reference range is not specifically limited here and can be adjusted according to parts of different specifications.

[0060] A200, obtain the actual welding current value at different times during the T time when the welding robot performs intelligent welding, and calibrate the actual welding current value as I x, x represents the number of the actual welding current value at different times within T time when the welding robot performs intelligent welding, x = 1, 2, 3, 4, ..., m, m is a positive integer;

[0061] It should be noted that during the welding process, a current sensor can be installed to monitor the welding current value of the welding robot in real time when performing intelligent welding. The actual value of the welding current is transmitted to the monitoring system through the current sensor, so that the current information can be obtained in real time;

[0062] A300, compare the actual welding current value obtained within T time with the optimal welding current reference range I min ~I max Compare and set the welding current that is not in the optimal reference range I min ~I max The actual welding current value between is defined as the non-optimal current value, and the non-optimal current value is calibrated as I y , y represents the number of the non-optimal current value obtained within T time, y=1, 2, 3, 4, ..., n, n is a positive integer;

[0063] A400, calculate the welding current abnormal concealment coefficient, the calculation expression is: [t1, t2] is the period of non-optimal current value obtained within T time, t1<t2,

[0064] From the calculation expression of the welding current abnormal concealment coefficient, it can be seen that the greater the performance value of the welding current abnormal concealment coefficient generated when the welding robot performs intelligent welding within the T time, the greater the hidden danger that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time, and vice versa, the smaller the hidden danger that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time;

[0065] The welding rate refers to the distance that the welding robot moves per unit time during the welding process. In the automobile manufacturing process, when the welding robot performs intelligent welding on parts of the same specification, the welding rate is the speed at which the welding robot welds the weld when completing the welding operation. The stability of the welding rate is a key parameter in the welding process, which affects the formation of the welding pool, the distribution of the welding temperature and the stability of the welding quality. The instability of the welding rate may have the following serious effects on the welding quality of the parts:

[0066] Uneven welds: Instability in welding rate can cause variations in weld width and depth, making the weld uneven, which can reduce weld consistency and reliability;

[0067] Welding defects: Unstable welding rate may lead to unstable formation of welding pool, which in turn causes defects such as porosity and slag inclusion, affecting welding quality;

[0068] Welding deformation: The instability of welding rate may cause the cooling speed of the weld pool to be different in different areas, thus causing welding deformation and affecting the size and shape of the parts;

[0069] Reduced welding strength: Unstable welding rate may lead to uneven metal structure in the weld pool, thus affecting the consistency and stability of weld strength;

[0070] Deterioration of weld quality: Instability in welding rate may lead to uneven metal composition in the weld pool, thus affecting the performance and quality of the weld;

[0071] Abnormal welding temperature: Unstable welding rate may lead to uneven temperature distribution of the welding pool, resulting in abnormal welding temperature and affecting welding quality and strength;

[0072] Unqualified welding quality: The instability of welding rate may cause the welding quality to not meet the requirements, making the welded parts unable to pass the quality inspection, affecting the quality of the overall product;

[0073] Therefore, monitoring the welding rate of the welding robot during intelligent welding can timely detect abnormal welding rate problems;

[0074] The logic of obtaining the welding speed fluctuation coefficient is as follows:

[0075] B100. Obtain the actual average welding rate of the welding robot for intelligent welding of parts of the same specification in different time periods within T time (the time in the selected time period can be all equal, or all unequal, or in the form of a cross, and the selection of time in the time period is not specifically limited here), and calibrate the actual welding rate as V k , k represents the number of the actual average welding rate of different time periods within T time when the welding robot performs intelligent welding on parts of the same specification, k = 1, 2, 3, 4, ..., N, N is a positive integer;

[0076] It should be noted that installing a displacement sensor or encoder during the welding process can monitor the moving distance and speed of the welding robot in real time, thereby calculating the actual average welding rate at different time periods;

[0077] B200. Calculate the standard deviation of the actual average welding rate at different time periods within T time when the welding robot performs intelligent welding, and calibrate the standard deviation of the actual average welding rate as R, then:

[0078]

[0079] ; Among them, V 平 The average value of the actual average welding rate at different time periods within T time when the welding robot performs intelligent welding is obtained by the calculation formula:

[0080] It can be seen from the actual average welding rate standard deviation R that the larger the performance value of the actual average welding rate standard deviation R, the worse the stability of the actual average welding rate at different time periods within the T time when the welding robot performs intelligent welding. Conversely, the better the stability of the actual average welding rate at different time periods within the T time when the welding robot performs intelligent welding.

[0081] B300, calculate the welding speed fluctuation coefficient, the calculation expression is: ββ V =ln(R 2 +1);

[0082] From the calculation expression of the welding speed fluctuation coefficient, it can be seen that the greater the performance value of the welding speed fluctuation coefficient generated when the welding robot performs intelligent welding within the T time, the greater the hidden danger that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time, and vice versa, the smaller the hidden danger that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time;

[0083] The software control information of the welding robot performing intelligent welding on parts of the same specification during automobile manufacturing includes the control path deviation coefficient. After collection, the control path deviation coefficient is calibrated as γγ S ;

[0084] When welding robots perform intelligent welding of parts of the same specification during automobile manufacturing, the deviation between the welding path controlled by the software and the pre-planned welding path may cause serious welding quality problems. The following are the possible effects of this deviation:

[0085] Mismatched welds: If the welding path controlled by the software deviates from the pre-planned welding path, it may cause mismatched welds, making the weld width and depth inconsistent, affecting the strength and consistency of the weld;

[0086] Uneven weld gap: Deviations may cause the weld gap to be inconsistent in different areas, resulting in insufficient weld filling and affecting the quality and appearance of the weld;

[0087] Welding deformation: Deviations between the software-controlled path and the pre-planned path may result in uneven heating distribution in the welding area, causing welding deformation and affecting the size and shape of the part;

[0088] Reduced weld quality: Deviations may result in inaccurate positioning of the welding gun or welding wire relative to the workpiece during welding, which can affect weld formation and quality;

[0089] Reduced welding strength: Deviation may cause some areas in the welding path to not be fully melted and bonded, resulting in reduced welding strength;

[0090] Porosity and slag inclusion: Software control path deviation may cause the gas in the weld to be unable to be discharged smoothly, forming pores and slag inclusions, affecting the quality of the weld;

[0091] Therefore, by monitoring the welding path controlled by the software when the welding robot performs intelligent welding, abnormal problems such as deviations between the welding path controlled by the software and the pre-planned welding path can be discovered in time;

[0092] The logic of obtaining the control path deviation coefficient is as follows:

[0093] C100, obtaining an actual software-controlled welding path and a pre-planned welding path when the welding robot performs intelligent welding, and marking the actual software-controlled welding path and the pre-planned welding path as L1 and L2, respectively;

[0094] It should be noted that welding robots are usually equipped with sensors and scanning technology, which can scan the surface of parts in real time and automatically generate welding paths based on the scanning results;

[0095] C200, dividing the actual software-controlled welding path L1 and the pre-planned welding path L2 when the welding robot performs intelligent welding into a plurality of points according to time points, and overlapping the points on the actual software-controlled welding path L1 and the points on the pre-planned welding path L2 according to time points, and then comparing and analyzing them;

[0096] It should be noted that OpenCV (Open Source Computer Vision Library) is a widely used open source image processing library that can be used to analyze and process image data in the real-time welding process. Through OpenCV, image information of the welding path and the pre-planned path can be obtained in real time, and compared and analyzed;

[0097] C300, input the actual software controlled welding path L1 and the pre-planned welding path L2 into the two-dimensional coordinate system, use Euclidean distance calculation to calculate the distance between the points on the actual software controlled welding path L1 and the points on the pre-planned welding path L2 at the same time, and calibrate the distance between the points on the actual software controlled welding path L1 and the points on the pre-planned welding path L2 at the same time as L w , w represents the number of the actual average welding rate of different time periods within T time when the welding robot performs intelligent welding on parts of the same specification, w = 1, 2, 3, 4, ..., p, p is a positive integer;

[0098] It should be noted that Euclidean distance is the most common distance calculation method, which is applicable to two-dimensional or three-dimensional coordinate points;

[0099] C400, calculate the control path deviation coefficient, the calculation expression is:

[0100] From the calculation expression of the control path deviation coefficient, it can be seen that the larger the performance value of the control path deviation coefficient generated when the welding robot performs intelligent welding within the T time, the greater the hidden danger that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time is, and vice versa, the smaller the hidden danger that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time is;

[0101] S102, comprehensively analyzing the processed welding physical parameter information and software control information when the welding robot performs intelligent welding in the automobile manufacturing process to generate a hidden danger assessment index;

[0102] Obtain the welding current abnormal concealment coefficient αα I , welding speed fluctuation coefficient ββ V and the control path deviation coefficient γγ S Finally, a data analysis model is established based on the acquired data information to generate the hidden danger assessment index YH δ , based on the formula:

[0103]

[0104] ; Where f1, f2, and f3 are the welding current abnormal concealment coefficients αα I , welding speed fluctuation coefficient ββ V And the control path deviation coefficient is calibrated as γγ S The preset proportional coefficient, and f1, f2, and f3 are all greater than 0;

[0105] It can be seen from the calculation formula that the greater the welding current abnormal concealment coefficient, the greater the welding speed fluctuation coefficient, and the greater the control path deviation coefficient generated when the welding robot performs intelligent welding within the time T, that is, the hidden danger assessment index YH generated when the welding robot performs intelligent welding within the time T δ The larger the performance value, the greater the hidden danger that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time. The smaller the welding current abnormal concealment coefficient, welding speed fluctuation coefficient and control path deviation coefficient generated by the welding robot when performing intelligent welding within T time, that is, the hidden danger assessment index YH generated by the welding robot when performing intelligent welding within T time. δThe smaller the performance value is, the smaller the hidden danger is that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time;

[0106] S103, comparing and analyzing the hidden danger assessment index generated when the welding robot performs intelligent welding in the automobile manufacturing process with a preset hidden danger assessment index reference threshold, and generating a high hidden danger risk signal and a low hidden danger risk signal;

[0107] Compare and analyze the hidden danger assessment index generated by the welding robot during intelligent welding in the automobile manufacturing process with the pre-set hidden danger assessment index reference threshold. If the hidden danger assessment index is greater than or equal to the hidden danger assessment index reference threshold, a high hidden danger risk signal is generated; if the hidden danger assessment index is less than the hidden danger assessment index reference threshold, a low hidden danger risk signal is generated;

[0108] S104. When a high hidden danger risk signal is generated during intelligent welding by a welding robot in the automobile manufacturing process, the parameters during welding are adjusted intelligently in a timely manner, and a hidden danger assessment index output after adjustment is comprehensively analyzed to generate an adjustment result signal, and different early warning prompts are issued for the adjustment result signal or no early warning prompt is issued;

[0109] When a high hidden danger risk signal is generated during intelligent welding by a welding robot in the automobile manufacturing process, the welding parameters are adjusted intelligently, and a data set is established for several hidden danger assessment indexes output after adjustment. The data set is calibrated as P, then P = {YH δ}, δ represents the number of the hidden danger assessment index in the data set, δ = 1, 2, 3, 4, ..., u, u is a positive integer;

[0110] Calculate the mean value and standard deviation of the hidden danger assessment index in the data set, and compare the mean value and standard deviation of the hidden danger assessment index with the pre-set reference threshold of the hidden danger assessment index and the pre-set reference threshold of the standard deviation, respectively. The comparison is divided into the following cases:

[0111] If the average value of the hidden danger assessment index is greater than or equal to the reference threshold value of the hidden danger assessment index, a signal of welding parameter adjustment failure is generated and transmitted to the prompt end, and an early warning prompt of welding parameter adjustment failure is issued through the prompt end to prompt relevant staff that the welding parameter adjustment has failed and the welding robot needs to be shut down for maintenance;

[0112] If the average value of the hidden danger assessment index is less than the reference threshold value of the hidden danger assessment index and the standard deviation of the hidden danger assessment index is greater than or equal to the reference threshold value of the standard deviation, a signal indicating that the welding parameter adjustment is unstable is generated and transmitted to the prompt end, and an early warning prompt indicating that the welding parameter adjustment is unstable is issued through the prompt end, prompting relevant staff that the welding parameter adjustment is unstable and the welding robot needs to be shut down for maintenance;

[0113] If the average value of the hidden danger assessment index is less than the reference threshold value of the hidden danger assessment index and the standard deviation of the hidden danger assessment index is less than the standard deviation reference threshold value, a signal of successful welding parameter adjustment is generated and the signal is transmitted to the prompt end, and no early warning prompt is issued through the prompt end.

[0114] The present invention monitors the parameters of the welding robot when performing intelligent welding on parts of the same specification during the automobile manufacturing process. If there is an abnormal hidden danger that the welding parameters of the welding robot are abnormal but not discovered and adjusted in time, the welding parameters are intelligently adjusted in time, effectively preventing the welding parameters of the welding robot from being abnormal but not discovered in time, ensuring that the welding robot performs efficient welding, and further facilitating efficient production of automobile manufacturing;

[0115] The present invention conducts a comprehensive analysis on the parameter adjustment of the welding robot when performing intelligent welding. If the parameter adjustment fails or the adjustment is unstable, the relevant staff will be notified in time to shut down the welding robot for maintenance to ensure that the welding robot is in an efficient welding state. Secondly, when an early warning prompt is issued, it can be understood whether the welding robot fails to adjust the parameters or the adjustment is unstable, which is convenient for maintenance personnel to reasonably analyze the possible faults of the welding robot.

[0116] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0117] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0118] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0119] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0120] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0121] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0123] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0124] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0125] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A parameter adjustment method for industrial production, characterized in that: The following steps are involved: S101, collecting multiple pieces of information when a welding robot performs intelligent welding on parts of the same specification during automobile manufacturing, including welding physical parameter information and software control information, and after collection, processing the welding physical parameter information and software control information during welding; The welding physical parameter information when the welding robot performs intelligent welding on parts of the same specification in the automobile manufacturing process includes the welding current anomaly concealment coefficient and the welding speed fluctuation coefficient. After collection, the welding current anomaly concealment coefficient and the welding speed fluctuation coefficient are calibrated as αα I and β V In the automobile manufacturing process, the software control information of the welding robot for intelligent welding of parts of the same specification includes the control path deviation coefficient. After collection, the control path deviation coefficient is calibrated as γγ S ; The logic for obtaining the welding current abnormal concealment coefficient is as follows: A100, obtain the optimal welding current reference range when the welding robot performs intelligent welding on parts of the same specification, and calibrate the optimal welding current reference range as I min ~I max ; A200, obtain the actual welding current value at different times during the T time when the welding robot performs intelligent welding, and calibrate the actual welding current value as I x , x represents the number of the actual welding current value at different times within T time when the welding robot performs intelligent welding, x = 1, 2, 3, 4, ..., m, m is a positive integer; A300, compare the actual welding current value obtained within T time with the optimal welding current reference range I min ~I max Compare and set the welding current that is not in the optimal reference range I min ~I max The actual welding current value between is defined as the non-optimal current value, and the non-optimal current value is calibrated as I y , y represents the number of the non-optimal current value obtained within T time, y=1, 2, 3, 4, ..., n, n is a positive integer; A400, calculate the welding current abnormal concealment coefficient, the calculation expression is: [t1, t2] is the period of non-optimal current value obtained within T time, t1 <t2, The logic of obtaining the welding speed fluctuation coefficient is as follows: B100, obtain the actual average welding rate of the welding robot for intelligent welding of parts of the same specification in different periods of time within T time, and calibrate the actual welding rate as V k , k represents the number of the actual average welding rate of different time periods within T time when the welding robot performs intelligent welding on parts of the same specification, k = 1, 2, 3, 4, ..., N, N is a positive integer; B200. Calculate the standard deviation of the actual average welding rate at different time periods within T time when the welding robot performs intelligent welding, and calibrate the standard deviation of the actual average welding rate as R, then: Among them, V 平 The average value of the actual average welding rate at different time periods within T time when the welding robot performs intelligent welding is obtained by the calculation formula: B300, calculate the welding speed fluctuation coefficient, the calculation expression is: ββ V =ln(R 2 +1); The logic of obtaining the control path deviation coefficient is as follows: C100, obtaining an actual software-controlled welding path and a pre-planned welding path when the welding robot performs intelligent welding, and marking the actual software-controlled welding path and the pre-planned welding path as L1 and L2, respectively; C200, dividing the actual software-controlled welding path L1 and the pre-planned welding path L2 when the welding robot performs intelligent welding into a plurality of points according to time points, and overlapping the points on the actual software-controlled welding path L1 and the points on the pre-planned welding path L2 according to time points, and then comparing and analyzing them; C300, input the actual software controlled welding path L1 and the pre-planned welding path L2 into the two-dimensional coordinate system, use Euclidean distance calculation to calculate the distance between the points on the actual software controlled welding path L1 and the points on the pre-planned welding path L2 at the same time, and calibrate the distance between the points on the actual software controlled welding path L1 and the points on the pre-planned welding path L2 at the same time as L w , w represents the number of the actual average welding rate of different time periods within T time when the welding robot performs intelligent welding on parts of the same specification, w = 1, 2, 3, 4, ..., p, p is a positive integer; C400, calculate the control path deviation coefficient, the calculation expression is: S102, comprehensively analyzing the processed welding physical parameter information and software control information when the welding robot performs intelligent welding in the automobile manufacturing process to generate a hidden danger assessment index; Obtain the welding current abnormal concealment coefficient αα I , welding speed fluctuation coefficient ββ V and the control path deviation coefficient γγ S Finally, a data analysis model is established based on the acquired data information to generate the hidden danger assessment index YH δ , based on the formula: Where f1, f2, and f3 are the welding current abnormal concealment coefficients αα I , welding speed fluctuation coefficient ββ V And the control path deviation coefficient is calibrated as γγ S The preset proportional coefficient, and f1, f2, and f3 are all greater than 0; S103, comparing and analyzing the hidden danger assessment index generated when the welding robot performs intelligent welding in the automobile manufacturing process with a preset hidden danger assessment index reference threshold, and generating a high hidden danger risk signal and a low hidden danger risk signal; S104. When a high hidden danger risk signal is generated when a welding robot performs intelligent welding in the automobile manufacturing process, the welding parameters are adjusted intelligently in a timely manner, and a comprehensive analysis is performed on the hidden danger assessment index output after the adjustment to generate an adjustment result signal, and different early warning prompts are issued for the adjustment result signal or no early warning prompt is issued.

2. The parameter adjustment method for industrial production according to claim 1, characterized in that: The hidden danger assessment index generated by the welding robot during intelligent welding in the automobile manufacturing process is compared and analyzed with the pre-set hidden danger assessment index reference threshold. If the hidden danger assessment index is greater than or equal to the hidden danger assessment index reference threshold, a high hidden danger risk signal is generated; if the hidden danger assessment index is less than the hidden danger assessment index reference threshold, a low hidden danger risk signal is generated.

3. The parameter adjustment method for industrial production according to claim 2, characterized in that: When a high hidden danger risk signal is generated during intelligent welding by a welding robot in the automobile manufacturing process, the welding parameters are adjusted intelligently, and a data set is established for several hidden danger assessment indexes output after adjustment. The data set is calibrated as P, then P = {YH δ }, δ represents the number of the hidden danger assessment index in the data set, δ = 1, 2, 3, 4, ..., u, u is a positive integer; Calculate the mean value and standard deviation of the hidden danger assessment index in the data set, and compare the mean value and standard deviation of the hidden danger assessment index with the pre-set reference threshold of the hidden danger assessment index and the pre-set reference threshold of the standard deviation, respectively. The comparison is divided into the following cases: If the average value of the hidden danger assessment index is greater than or equal to the reference threshold value of the hidden danger assessment index, a signal of welding parameter adjustment failure is generated and transmitted to the prompt end, and an early warning prompt of welding parameter adjustment failure is issued through the prompt end to prompt relevant staff that the welding parameter adjustment has failed and the welding robot needs to be shut down for maintenance; If the average value of the hidden danger assessment index is less than the reference threshold value of the hidden danger assessment index and the standard deviation of the hidden danger assessment index is greater than or equal to the reference threshold value of the standard deviation, a signal indicating that the welding parameter adjustment is unstable is generated and transmitted to the prompt end, and an early warning prompt indicating that the welding parameter adjustment is unstable is issued through the prompt end, prompting relevant staff that the welding parameter adjustment is unstable and the welding robot needs to be shut down for maintenance; If the average value of the hidden danger assessment index is less than the reference threshold value of the hidden danger assessment index and the standard deviation of the hidden danger assessment index is less than the standard deviation reference threshold value, a signal of successful welding parameter adjustment is generated and the signal is transmitted to the prompt end, and no early warning prompt is issued through the prompt end.

4. An industrial production parameter adjustment device, used to execute an industrial production parameter adjustment method as described in any one of claims 1 to 3.

Citation Information

Patent Citations

  • Self-adaptive robot arc additive manufacturing system and method

    CN112570853A

  • Industrial robot system based on visual module with fusion of laser and visible light

    CN113172307A

  • Non-digital welding machine welding process quality monitoring system and method

    CN114131145A

  • Intelligent dynamic control method for flow velocity of welding shielding gas under argon arc welding scene

    CN116441673A

  • Systems, methods, and apparatuses for monitoring weld quality

    US20150060424A1