Welding quality detection method and system
By collecting the working parameters of welding equipment and weld quality parameters, combining the image detection model to identify defects, and applying pressure to detect welding strength, the problem of the inability to comprehensively detect welding quality in the existing technology is solved, and a comprehensive and accurate evaluation of welding quality is achieved.
Patent Information
- Application Number
- CN202411281792.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The prior art cannot conduct comprehensive inspection of welding quality based on welding process quality and weld quality.
The working parameters of the welding equipment are collected through sensor equipment, weld quality parameters and images are obtained, defects are identified in combination with the image detection model, pressure is applied to detect welding strength, comprehensively score welding technology, weld and strength quality, and generate welding quality inspection reports.
It has achieved comprehensive and accurate inspection of the welding quality of welding products, and improved the comprehensiveness and accuracy of inspection.
Smart Images

Figure CN119057178A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of welding quality detection, and in particular to a welding quality detection method and system. Background Art
[0002] In the related art, CN108760819A discloses a welding quality detection device and a detection method thereof, including a mounting frame, the mounting frame is provided with a detection platform, the detection platform is provided with a detection plug, the detection plug is provided with a detection slot, the detection slot is provided with a plug-in portion and a test probe; a loading part; and a driving mechanism. The driving mechanism first moves the loading part to a first preset position so that the welding part of the product to be tested matches the plug-in portion, and then the driving mechanism moves the loading part to a second preset position so that the welding part of the product to be tested matches the test probe to test whether the welding is qualified. Since the welding part and the plug-in portion are first matched, if there are problems such as loose welding in the welding part, the friction generated during the plug-in process will cause the unreliable part to fall off, so that it cannot pass the test when it is matched with the test probe later, thereby obtaining a test result of whether the welding part is qualified. The use of this mechanism does not require manual visual inspection, which not only improves the welding detection efficiency, but also reduces the production cost.
[0003] CN117629738A discloses a welding quality detection method, which includes: performing a tensile test on a welded part, the welded part is obtained by welding a first connecting part and a second connecting part, and the tensile strength of the first connecting part is greater than the tensile strength of the second connecting part, after the welded part passes the tensile test, obtaining a welded part residue, the welded part residue is composed of the first connecting part and the weld nugget residue, determining the total weld print area and the total weld nugget residue area on the welded part residue, and determining the welding quality detection result according to the ratio of the total weld nugget residue area to the total weld print area. After the welded part passes the tensile test, the welded part residue after the tensile test is continued to be obtained, and the welding quality detection result is determined according to the ratio of the total weld nugget residue area on the welded part residue to the total weld print area, thereby improving the accuracy of the welding quality detection result, and being able to make a comprehensive and accurate assessment of the reliability and current carrying capacity of the battery tab welding.
[0004] Based on the above related technologies, the accuracy of welding quality inspection results can be improved. However, the related technologies do not consider the influence of welding process quality and weld quality on welding quality inspection results, that is, it is impossible to conduct a comprehensive inspection of welding quality based on welding process quality and weld quality.
[0005] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art. Summary of the invention
[0006] The present invention provides a welding quality detection method and system, which can solve the technical problem that the related technology cannot comprehensively detect the welding quality according to the welding process quality and the weld quality.
[0007] According to a first aspect of the present invention, there is provided a method for detecting welding quality, comprising:
[0008] At multiple moments in the working cycle, the working parameters of the welding equipment are collected by the sensor equipment, wherein the working parameters include: welding current, arc voltage and welding line energy;
[0009] Determine a welding process quality score based on the working parameters;
[0010] Sampling all welding products in the current batch to obtain sample welding products;
[0011] Acquire weld quality parameters of sample welding products, wherein the weld quality parameters include: weld width, weld excess height, weld calculated thickness and weld penetration;
[0012] Acquire the weld seam image of the sample welding product through the image acquisition device;
[0013] Determining a weld quality score of a sample welded product according to the weld quality parameter and the weld image;
[0014] At multiple moments in the welding strength test cycle, a uniformly increasing pressure is applied to the sample welding product through the testing device, and pressure data of the testing device and the bending angle of the sample welding product are obtained;
[0015] Determining a welding strength quality score of a sample welding product according to the pressure data and the bending angle;
[0016] Determine an overall welding quality score according to the welding process quality score, the weld quality score and the welding strength quality score;
[0017] A welding quality inspection report is generated based on the overall welding quality score.
[0018] According to a second aspect of the present invention, there is provided a welding quality detection system, comprising:
[0019] A welding equipment module, used to collect working parameters of the welding equipment through sensor equipment at multiple moments in a working cycle, wherein the working parameters include: welding current, arc voltage and welding line energy;
[0020] A welding process quality module, used to determine a welding process quality score according to the working parameters;
[0021] A sampling module is used to sample all welding products in the current batch to obtain sample welding products;
[0022] An appearance parameter module is used to obtain weld quality parameters of sample welding products, wherein the weld quality parameters include: weld width, weld excess height, weld calculated thickness and penetration depth;
[0023] An image acquisition module, used to acquire a weld image of a sample welding product through an image acquisition device;
[0024] A weld quality module, used to determine a weld quality score of a sample welded product according to the weld quality parameter and the weld image;
[0025] A detection data module, used to apply uniformly increasing pressure to the sample welding product through the detection equipment at multiple moments in the welding strength detection cycle, and obtain the pressure data of the detection equipment and the bending angle of the sample welding product;
[0026] A welding strength quality module, used to determine a welding strength quality score of a sample welding product according to the pressure data and the bending angle;
[0027] An overall welding quality module, used to determine an overall welding quality score according to the welding process quality score, the weld quality score and the welding strength quality score;
[0028] The quality inspection report module is used to generate a welding quality inspection report based on the overall welding quality score.
[0029] Technical effect: According to the present invention, the welding quality of welding products can be comprehensively tested through the three aspects of welding process quality, weld quality and welding strength quality of welding products, so as to more accurately test the welding quality of welding products, and improve the comprehensiveness and accuracy of welding quality testing. When determining the welding process quality score, the welding process quality score can be determined according to the working parameters, the real-time equipment working state vector and the standard equipment working state vector. During the calculation process, the welding process status and working stability status of the welding equipment are used to evaluate the quality of the welding process, thereby improving the comprehensiveness and accuracy of the welding process quality score. When determining the weld quality score, the weld quality score of the sample welding product can be determined according to the crack identification results, the slag inclusion identification results, the lack of fusion identification results, the lack of penetration identification results and the weld quality parameters. During the calculation process, the intrinsic quality status of the weld of the sample welding product can be accurately analyzed according to the weld quality parameters, and various defects in the weld can be detected by the artificial intelligence model, and the appearance quality status of the weld of the sample welding product can be determined according to the detection results. Further, based on the intrinsic quality status and appearance quality status of the weld of the sample welding product, the weld quality of the sample welding product is comprehensively evaluated, thereby improving the comprehensiveness and accuracy of the weld quality score. When determining the welding strength quality score, the welding strength quality score of the sample welding product can be determined based on the pressure data, the bending angle and the standard deviation of the first ratio. The welding strength quality of the sample welding product can be evaluated from three aspects: the stability of the bending resistance of the sample welding product, the ultimate bending resistance and the ultimate bending angle, thereby improving the comprehensiveness and accuracy of the welding strength quality score.
[0030] It should be understood that the above general description and the following detailed description are exemplary and explanatory only and do not limit the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other embodiments can be obtained based on these drawings without creative work.
[0032] Figure 1 A schematic diagram of an operation and maintenance evaluation and control platform based on a smart building according to an embodiment of the present invention is exemplarily shown;
[0033] Figure 2 The following is a flow chart of an operation and maintenance evaluation and control method based on a smart building according to an embodiment of the present invention. DETAILED DESCRIPTION
[0034] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0035] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
[0036] Figure 1 A schematic flow chart of a method for detecting welding quality according to an embodiment of the present invention is exemplarily shown, the method comprising:
[0037] Step S101, collecting working parameters of the welding equipment through a sensor device at multiple moments in a working cycle, wherein the working parameters include: welding current, arc voltage and welding line energy;
[0038] Step S102, determining a welding process quality score according to the working parameters;
[0039] Step S103, sampling all welding products in the current batch to obtain sample welding products;
[0040] Step S104, obtaining weld quality parameters of the sample welding product, wherein the weld quality parameters include: weld width, weld excess height, weld calculated thickness and weld penetration;
[0041] Step S105, obtaining a weld image of a sample welding product through an image acquisition device;
[0042] Step S106, determining a weld quality score of the sample welding product according to the weld quality parameter and the weld image;
[0043] Step S107, at multiple moments in the welding strength detection cycle, a uniformly increasing pressure is applied to the sample welding product through the detection device, and pressure data of the detection device and the bending angle of the sample welding product are obtained;
[0044] Step S108, determining a welding strength quality score of the sample welding product according to the pressure data and the bending angle;
[0045] Step S109, determining an overall welding quality score according to the welding process quality score, the weld quality score and the welding strength quality score;
[0046] Step S110, generating a welding quality inspection report according to the overall welding quality score.
[0047] According to the welding quality detection method of the embodiment of the present invention, the welding quality of the welding product can be comprehensively detected through three aspects: welding process quality, weld quality and welding strength quality of the welding product, so as to more accurately detect the welding quality of the welding product and improve the comprehensiveness and accuracy of welding quality detection.
[0048] According to one embodiment of the present invention, in step S101, at multiple moments in a working cycle, working parameters of a welding device are collected by a sensor device, wherein the working parameters include: welding current, arc voltage and welding line energy.
[0049] For example, the sensor equipment in the welding equipment monitoring system collects the connection current, arc voltage and welding line energy of the welding equipment when it is working. The welding current has an important influence on the melting rate, the penetration depth of the base material, the intrinsic quality of the weld and the performance of the welded joint. Too large a welding current will lead to defects such as undercut and burn-through, while too small a welding current may cause slag inclusion and incomplete penetration. The increase in arc voltage will lead to a significant increase in the weld width, while the weld thickness and excess height will be slightly reduced. The welding line energy has an important influence on the formation and quality of the weld.
[0050] According to an embodiment of the present invention, in step S102, a welding process quality score is determined according to the working parameters.
[0051] According to one embodiment of the present invention, step S102 includes:
[0052] Determining a real-time equipment operating state vector according to the welding current, the arc voltage and the welding line energy;
[0053] Determine the characteristics of the welding base material and the welding process;
[0054] Determining a standard welding current, a standard arc voltage and a standard welding energy input according to the characteristics of the welding base material and the welding process;
[0055] Determining a standard equipment working state vector according to the standard welding current, the standard arc voltage and the standard welding line energy;
[0056] A welding process quality score is determined according to the working parameters, the real-time equipment working state vector and the standard equipment working state vector.
[0057] For example, due to the different characteristics of the welding base material and the welding process, the requirements for welding current, arc voltage and welding line energy are also different. According to the characteristics of the welding base material and the welding process, the standard welding current, standard arc voltage and standard welding line energy are determined. Based on the welding current, arc voltage, welding line energy, standard welding current, standard arc voltage and standard welding line energy, the quality of the welding process is evaluated to determine the welding process quality score.
[0058] According to one embodiment of the present invention, determining the welding process quality score according to the working parameters, the real-time equipment working state vector and the standard equipment working state vector includes: determining the welding process quality score Wt according to formula (1),
[0059]
[0060] Among them, max is the maximum value function, min is the minimum value function, if is the conditional function, Ss T is the preset similarity threshold, Cu k is the welding current at the kth moment of the working cycle, Av k is the arc voltage at the kth moment of the working cycle, Wle k is the welding line energy at the kth moment of the working cycle, is the real-time device working state vector at the kth moment of the working cycle, for The transposed vector of Cu T is the standard welding current, Av T is the standard arc voltage, Wle T is the standard welding line energy, is the working state vector of the standard equipment, K is the number of moments in the working cycle, k≤K, k and K are both positive integers.
[0061] According to one embodiment of the present invention, It is the cosine similarity between the real-time equipment working state vector and the standard equipment working state vector at the kth moment of the working cycle. The larger the cosine similarity, the smaller the difference between the welding current, arc voltage and welding line energy of the welding equipment at the kth moment of the working cycle and the standard welding current, standard arc voltage and standard welding line energy.
[0062] According to one embodiment of the present invention, in formula (1), the conditional function The value of includes the following two cases, when it satisfies When the condition is met, the cosine similarity between the real-time equipment working state vector at the kth moment of the working cycle and the standard equipment working state vector is greater than the preset similarity threshold, indicating that the welding current, arc voltage and welding line energy of the welding equipment at the kth moment of the working cycle are less different from the standard welding current, standard arc voltage and standard welding line energy, the welding process is good, and the value of the condition function is 1. When it is not met When the condition is met, it means that the welding current, arc voltage and welding line energy at the kth moment in the working cycle are greatly different from the standard welding current, standard arc voltage and standard welding line energy, the welding process condition is poor, and the value of the condition function is 0. It is the ratio of the number of moments with better welding process conditions in the working cycle to the number of moments in the working cycle. The larger the ratio is, the better the overall welding process condition in the working cycle is.
[0063] According to one embodiment of the present invention, It is the ratio of the difference between the maximum and minimum values of the welding current of the welding equipment in the working cycle to the maximum value of the welding current, indicating the relative difference between the maximum and minimum values of the welding current of the welding equipment in the working cycle. The smaller the ratio is, the smaller the difference between the maximum and minimum values of the welding current of the welding equipment in the working cycle is. The larger the value, the more stable the welding current of the welding equipment during the working cycle. It is the ratio of the difference between the maximum and minimum values of the arc voltage of the welding equipment in the working cycle to the maximum value of the arc voltage, indicating the relative difference between the maximum and minimum values of the arc voltage of the welding equipment in the working cycle. The smaller the ratio is, the smaller the difference between the maximum and minimum values of the arc voltage of the welding equipment in the working cycle is. The larger the value, the more stable the arc voltage of the welding equipment during the working cycle. It is the ratio of the difference between the maximum and minimum values of the welding line energy of the welding equipment in the working cycle to the maximum value of the welding line energy, which indicates the relative difference between the maximum and minimum values of the welding line energy of the welding equipment in the working cycle. The smaller the ratio is, the smaller the difference between the maximum and minimum values of the welding line energy of the welding equipment in the working cycle is. The larger the value, the more stable the welding line energy of the welding equipment during the working cycle.
[0064]
[0065] The working condition of the welding equipment during the working cycle is determined based on the stable condition of the welding current, the stable condition of the arc voltage and the stable condition of the welding line capacity.
[0066] In this way, the welding process quality score can be determined based on the working parameters, real-time equipment working state vector and standard equipment working state vector. During the calculation process, the welding process status and working stability status of the welding equipment are used to evaluate the quality of the welding process, thereby improving the comprehensiveness and accuracy of the welding process quality score.
[0067] According to an embodiment of the present invention, in step S103, sampling is performed among all welding products in the current batch to obtain sample welding products.
[0068] For example, random sampling is performed among all welding products in a current batch to obtain sample welding products.
[0069] According to an embodiment of the present invention, in step S104, the weld quality parameters of the sample welding product are obtained, wherein the weld quality parameters include: weld width, weld excess height, weld calculated thickness and penetration depth.
[0070] For example, the weld width, weld reinforcement, calculated weld thickness and penetration depth of the sample welding product can be obtained through measuring instruments. The weld width is the maximum dimension of the weld perpendicular to the welding direction. A weld width that is too wide or too narrow may affect the mechanical properties of the weld joint. The weld reinforcement is the maximum distance between the weld surface and the parent material surface. Too high reinforcement may cause stress concentration and affect the fatigue strength of the welded joint. Too low reinforcement may reduce the bearing capacity of the weld. The calculated weld thickness is the thickness of the weldment. The calculated weld thickness directly affects the strength and stability of the welded joint. The penetration depth is the depth to which the parent material melts under the action of the welding heat source. The size of the penetration depth directly affects the bonding strength between the weld and the parent material.
[0071] According to an embodiment of the present invention, in step S105, a weld image of a sample welding product is acquired by an image acquisition device.
[0072] For example, a camera is used to collect weld seam images of sample welded products.
[0073] According to an embodiment of the present invention, in step S106, a weld quality score of the sample welded product is determined according to the weld quality parameters and the weld image.
[0074] According to one embodiment of the present invention, step S106 includes:
[0075] In the weld image, identifying whether there is a crack in the weld by using an image detection model, and determining a crack identification result;
[0076] In the weld image, identifying whether there is slag inclusion in the weld by using an image detection model, and determining a slag inclusion identification result;
[0077] In the weld image, identifying whether there is a lack of fusion phenomenon in the weld by using an image detection model, and determining a lack of fusion identification result;
[0078] In the weld image, identifying whether there is a lack of penetration phenomenon in the weld by using an image detection model, and determining a lack of penetration identification result;
[0079] A weld quality score of the sample welded product is determined according to the crack identification result, the slag inclusion identification result, the lack of fusion identification result, the lack of penetration identification result and the weld quality parameter.
[0080] For example, the image detection model is a type of deep learning model. By training the image detection model with historical data, the image detection model can identify whether there are welding defects in the weld image. Welding defects can seriously reduce the mechanical properties and durability of the welded joint. The image detection model is used to identify whether there is a crack in the weld. If there is no crack in the weld, the crack identification result is 1, if there is a crack in the weld, the crack identification result is 0. The image detection model is used to identify whether there is slag inclusion in the weld. If there is no slag inclusion in the weld, the slag inclusion identification result is 1, if there is slag inclusion in the weld, the slag inclusion identification result is 0. The image detection model is used to identify whether there is incomplete fusion in the weld. If there is no incomplete fusion in the weld, the incomplete fusion identification result is 1, if there is incomplete fusion in the weld, the incomplete fusion identification result is 0. The image detection model is used to identify whether there is incomplete penetration in the weld. If there is no incomplete penetration in the weld, the incomplete penetration identification result is 1, if there is incomplete penetration in the weld, the incomplete penetration identification result is 0. According to the crack identification results, slag inclusion identification results, incomplete fusion identification results, incomplete penetration identification results and weld quality parameters, the quality of the weld is evaluated to determine the weld quality score of the sample welding product.
[0081] According to one embodiment of the present invention, the weld quality score of the sample welding product is determined according to the crack identification result, the slag inclusion identification result, the lack of fusion identification result, the lack of penetration identification result and the weld quality parameter, including: determining the weld quality score Wq of the i-th sample welding product according to formula (2): i ,
[0082]
[0083] Among them, α1, α2, α3 and α4 are preset weights, if is the conditional function, Ww i is the weld width of the i-th sample welding product, Ww T is the preset weld width threshold, Wr i is the weld reinforcement of the i-th sample welding product, Wr T is the preset weld height threshold, Tti Calculate the weld thickness of the i-th sample welded product, Ff T is the preset weld formation factor threshold, Df i is the penetration depth of the ith sample welding product, Df T is the preset penetration threshold, Fl i is the crack identification result of the i-th sample welding product, Si i is the slag inclusion identification result of the i-th sample welding product, Lof i is the lack of fusion identification result of the i-th sample welding product, Lop i is the incomplete penetration identification result of the i-th sample welding product,
[0084] The logical operator is "or".
[0085] According to one embodiment of the present invention, is the relative difference between the weld width of the i-th sample welding product and the preset weld width threshold. The smaller the ratio is, the smaller the difference between the weld width of the i-th sample welding product and the preset weld width threshold is. The larger the value of is, the more likely it is that the mechanical properties of the weld joint will be affected if the weld width is too wide or too narrow. The larger the value of , the higher the weld quality of the i-th sample welding product. is the relative difference between the weld reinforcement of the i-th sample welding product and the preset weld reinforcement threshold. The smaller the ratio is, the smaller the difference between the weld reinforcement of the i-th sample welding product and the preset weld reinforcement threshold is. The larger the value, the higher the weld height may lead to stress concentration and affect the fatigue strength of the welded joint. If the weld height is too low, the load-bearing capacity of the weld may be reduced. The larger the value of , the higher the weld quality of the i-th sample welding product. is the ratio of the weld width of the i-th sample welding product to the calculated weld thickness of the i-th sample welding product, which represents the weld formation coefficient of the i-th sample welding product. It represents the relative difference between the weld forming coefficient of the i-th sample welding product and the preset weld forming coefficient threshold. The larger the ratio is, the larger the weld forming coefficient of the i-th sample welding product is. Since a too small forming coefficient may lead to poor weld forming and affect the quality of the welded joint, The larger the value of , the higher the weld quality of the i-th sample welding product. is the relative difference between the penetration depth of the i-th sample welding product and the preset penetration depth threshold. The smaller the ratio is, the smaller the difference between the penetration depth of the i-th sample welding product and the preset penetration depth threshold is. The larger the value, the greater the penetration depth will be, the lower the bonding strength between the weld and the base material will be. The larger the value of , the higher the weld quality of the i-th sample welding product.
[0086] To determine the intrinsic quality status of the weld according to the weld width, weld reinforcement, weld formation factor and penetration depth of the i-th sample welding product.
[0087] According to one embodiment of the present invention, in formula (2), if {(Fl i =0)or(Si i =0)or(Lof i =0)or(Lop i =0), 1, 0} include the following two cases, when satisfying (Fl i =0)or(Si i =0)or(Lof i =0)or(Lop i =0), there are cracks or slag inclusions or incomplete fusion or incomplete penetration in the weld of the i-th sample welding product, indicating that there are defects in the weld of the i-th sample welding product, and the appearance quality of the i-th sample welding product is poor. The value of the conditional function is 1. If (Fl i =0)or(Si i =0)or(Lof i =0)or(Lop i =0), it means that there is no defect in the weld of the i-th sample welded product, the appearance quality of the i-th sample welded product is high, and the value of the conditional function is 0.
[0088] In this way, the weld quality score of the sample welding product can be determined based on the crack identification results, slag inclusion identification results, lack of fusion identification results, lack of penetration identification results and weld quality parameters. During the calculation process, the intrinsic quality status of the weld of the sample welding product can be accurately analyzed based on the weld quality parameters, and various defects in the weld can be detected by the artificial intelligence model, and the appearance quality status of the weld of the sample welding product can be determined based on the detection results. Furthermore, based on the intrinsic quality status and appearance quality status of the weld of the sample welding product, the weld quality of the sample welding product is comprehensively evaluated, thereby improving the comprehensiveness and accuracy of the weld quality score.
[0089] According to an embodiment of the present invention, in step S107, at multiple moments in the welding strength detection cycle, a uniformly increasing pressure is applied to the sample welding product by the detection device, and pressure data of the detection device and the bending angle of the sample welding product are obtained.
[0090] For example, at multiple moments in the welding strength test cycle, the sample welded product is placed on a bending machine, and the bending machine applies uniformly increasing pressure to the sample welded product, gradually increasing the bending angle of the sample welded product until the sample welded product breaks, and recording the pressure data of the bending machine and the bending angle of the sample welded product.
[0091] According to an embodiment of the present invention, in step S108, the welding strength quality score of the sample welding product is determined according to the pressure data and the bending angle.
[0092] According to one embodiment of the present invention, step S108 includes:
[0093] determining a first ratio according to the bending angle and the pressure data;
[0094] Determine a standard deviation of the first ratio according to the first ratios at multiple moments in the welding strength detection cycle;
[0095] A welding strength quality score of the sample welding product is determined according to the pressure data, the bending angle and the standard deviation of the first ratio.
[0096] For example, a first ratio is determined based on the ratio of the bending angle and the pressure data; an average of multiple first ratios is calculated based on the first ratios at multiple moments in the welding strength detection cycle, and then the standard deviation of the first ratio is determined based on the average of the first ratios; further, the welding strength of the sample welding product can be evaluated based on the pressure data, the bending angle and the standard deviation of the first ratio to determine the welding strength quality score of the sample welding product.
[0097] According to one embodiment of the present invention, determining the welding strength quality score of the sample welding product according to the pressure data, the bending angle and the standard deviation of the first ratio includes: determining the welding strength quality score Ws of the i-th sample welding product according to formula (3): i ,
[0098]
[0099] Among them, β1, β2 and β3 are preset weights, α p is the preset multiple, if is the conditional function, Ba i,j Pd is the bending angle of the i-th sample welding product at the j-th moment of the welding strength detection cycle, i,j is the pressure data of the i-th sample welding product at the j-th moment of the welding strength test cycle, is the first ratio of the i-th sample welding product at the j-th moment of the welding strength detection cycle, is the standard deviation of the first ratio, Ba i,eis the bending angle of the i-th sample welding product at the end of the welding strength test cycle, Ba T is the preset bending angle threshold, Pd i,e is the pressure data of the i-th sample welding product at the end of the welding strength test cycle, Pd T is the preset pressure data threshold, m is the number of moments in the welding strength detection cycle, j≤m, and both j and m are positive integers.
[0100] According to one embodiment of the present invention, is the first ratio of the i-th sample welding product at the j-th moment of the welding strength test cycle, indicating the bending angle of the i-th sample welding product under unit pressure at the j-th moment of the welding strength test cycle, indicating the bending resistance of the sample welding product. In formula (3), the conditional function The value of includes the following two cases, when satisfying When the condition is met, it means that the first ratio of the i-th sample welding product at the j-th moment of the welding strength detection cycle is within an interval with the average first ratio as the center of the interval and the standard deviation of twice the preset multiple as the interval length, and the value of the condition function is 1. When it is not met When the condition is met, the value of the conditional function is 0. If the first ratio of the i-th sample welding product at the j-th moment of the welding strength detection cycle meets the above conditions, it means that the deviation between the first ratio at the j-th moment and the mean is small, indicating that the anti-bending ability of the i-th sample welding product at the j-th moment of the welding strength detection cycle is relatively stable. Otherwise, it can be considered that the deviation between the first ratio at the j-th moment and the mean is large, indicating that the anti-bending ability of the i-th sample welding product at the j-th moment of the welding strength detection cycle is abnormal. It is the ratio between the number of moments when the anti-bending ability is relatively stable and the number of moments in the welding strength detection cycle. The larger the ratio is, the more stable the anti-bending ability is at multiple moments in the welding strength detection cycle, and the higher the welding strength quality of the sample welding product.
[0101] According to one embodiment of the present invention, is the relative difference between the bending angle of the i-th sample welding product at the end of the welding strength detection cycle and the preset bending angle threshold. The smaller the ratio, The larger the value of , the smaller the difference between the bending angle of the i-th sample welding product at the end of the welding strength detection cycle and the preset bending angle threshold, and the higher the welding strength quality of the i-th sample welding product. It is the relative difference between the pressure data of the i-th sample welding product at the end of the welding strength detection cycle and the preset pressure data threshold. The larger the ratio is, the greater the ultimate bending resistance of the sample welding product is and the higher the welding strength quality is.
[0102] In this way, the welding strength quality score of the sample welding product can be determined based on the pressure data, bending angle and standard deviation of the first ratio. The welding strength quality of the sample welding product can be evaluated from three aspects: the stability of the bending resistance of the sample welding product, the ultimate bending resistance and the ultimate bending angle, thereby improving the comprehensiveness and accuracy of the welding strength quality score.
[0103] According to one embodiment of the present invention, in step S109, the overall welding quality score is determined according to the welding process quality score, the weld quality score and the welding strength quality score.
[0104] According to one embodiment of the present invention, step S109 includes:
[0105] Determine the welding quality score of the i-th sample welding product by taking a weighted sum of the weld quality score of the i-th sample welding product and the welding strength quality score of the i-th sample welding product;
[0106] Determine a qualified identification result of the i-th sample welding product according to the welding quality score of the i-th sample welding product and a set welding quality score threshold;
[0107] Determine the number of sample welded products;
[0108] According to the number of the sample welding products, the qualified identification results of each sample welding product are summed up to determine the overall qualified identification result;
[0109] determining a second ratio according to the overall qualified identification result and the number of the sample welding products;
[0110] An overall welding quality score is determined according to the second ratio and the welding process quality score.
[0111] For example, if the welding quality score of the i-th sample welding product is greater than or equal to the set welding quality score threshold, the qualified identification result of the i-th sample welding product is 1; if the welding quality score of the i-th sample welding product is less than the set welding quality score threshold, the qualified identification result of the i-th sample welding product is 0; the qualified identification results of each sample welding product are summed according to the number of sample welding products to determine the overall qualified identification result; a second ratio is determined according to the ratio of the overall qualified identification result to the number of sample welding products, and the larger the second ratio is, the more qualified sample welding products are; the overall welding quality score is determined according to the product of the second ratio and the welding process quality score.
[0112] According to an embodiment of the present invention, in step S110, a welding quality inspection report is generated according to the overall welding quality score.
[0113] For example, if the overall welding quality score is greater than or equal to the set overall welding quality score threshold, the welding quality inspection is qualified; if the overall welding quality score is less than the set overall welding quality score threshold, the welding quality inspection is unqualified.
[0114] According to the welding quality detection method of the embodiment of the present invention, the welding quality of the welding product can be comprehensively detected through the three aspects of the welding process quality, weld quality and welding strength quality of the welding product, so as to more accurately detect the welding quality of the welding product, and improve the comprehensiveness and accuracy of the welding quality detection. When determining the welding process quality score, the welding process quality score can be determined according to the working parameters, the real-time equipment working state vector and the standard equipment working state vector. During the calculation process, the welding process status and working stability status of the welding equipment are used to evaluate the quality of the welding process, thereby improving the comprehensiveness and accuracy of the welding process quality score. When determining the weld quality score, the weld quality score of the sample welding product can be determined based on the crack identification results, slag inclusion identification results, lack of fusion identification results, lack of penetration identification results and weld quality parameters. During the calculation process, the intrinsic quality status of the weld of the sample welding product can be accurately analyzed based on the weld quality parameters, and various defects in the weld can be detected by the artificial intelligence model, and the appearance quality status of the weld of the sample welding product can be determined based on the detection results. Further, based on the intrinsic quality status and appearance quality status of the weld of the sample welding product, the weld quality of the sample welding product is comprehensively evaluated, thereby improving the comprehensiveness and accuracy of the weld quality score. When determining the welding strength quality score, the welding strength quality score of the sample welding product can be determined based on the pressure data, the bending angle and the standard deviation of the first ratio. The welding strength quality of the sample welding product can be evaluated from three aspects: the stable state of the bending resistance of the sample welding product, the ultimate bending resistance and the ultimate bending angle, thereby improving the comprehensiveness and accuracy of the welding strength quality score.
[0115] Figure 2 A block diagram of a welding quality detection system according to an embodiment of the present invention is exemplarily shown, wherein the system comprises:
[0116] A welding equipment module, used to collect working parameters of the welding equipment through sensor equipment at multiple moments in a working cycle, wherein the working parameters include: welding current, arc voltage and welding line energy;
[0117] A welding process quality module, used to determine a welding process quality score according to the working parameters;
[0118] A sampling module is used to sample all welding products in the current batch to obtain sample welding products;
[0119] An appearance parameter module is used to obtain weld quality parameters of sample welding products, wherein the weld quality parameters include: weld width, weld excess height, weld calculated thickness and penetration depth;
[0120] An image acquisition module, used to acquire a weld image of a sample welding product through an image acquisition device;
[0121] A weld quality module, used to determine a weld quality score of a sample welded product according to the weld quality parameter and the weld image;
[0122] A detection data module, used to apply uniformly increasing pressure to the sample welding product through the detection equipment at multiple moments in the welding strength detection cycle, and obtain the pressure data of the detection equipment and the bending angle of the sample welding product;
[0123] A welding strength quality module, used to determine a welding strength quality score of a sample welding product according to the pressure data and the bending angle;
[0124] An overall welding quality module, used to determine an overall welding quality score according to the welding process quality score, the weld quality score and the welding strength quality score;
[0125] The quality inspection report module is used to generate a welding quality inspection report based on the overall welding quality score.
[0126] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.
[0127] It should be understood by those skilled in the art that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.
Claims
1. A method for detecting welding quality, It is characterized in that include: At multiple moments in the working cycle, the working parameters of the welding equipment are collected by the sensor equipment, wherein the working parameters include: welding current, arc voltage and welding line energy; Determine a welding process quality score based on the working parameters; Sampling all welding products in the current batch to obtain sample welding products; Acquire weld quality parameters of sample welding products, wherein the weld quality parameters include: weld width, weld excess height, weld calculated thickness and weld penetration; Acquire the weld seam image of the sample welding product through the image acquisition device; Determining a weld quality score of a sample welded product according to the weld quality parameter and the weld image; At multiple moments in the welding strength test cycle, a uniformly increasing pressure is applied to the sample welding product through the testing device, and pressure data of the testing device and the bending angle of the sample welding product are obtained; Determining a welding strength quality score of a sample welding product according to the pressure data and the bending angle; Determine an overall welding quality score according to the welding process quality score, the weld quality score and the welding strength quality score; A welding quality inspection report is generated based on the overall welding quality score.
2. The method for detecting welding quality according to claim 1, It is characterized in that Based on the working parameters, determine the welding process quality score, including: Determining a real-time equipment operating state vector according to the welding current, the arc voltage and the welding line energy; Determine the characteristics of the welding base material and the welding process; Determining a standard welding current, a standard arc voltage and a standard welding energy input according to the characteristics of the welding base material and the welding process; Determining a standard equipment working state vector according to the standard welding current, the standard arc voltage and the standard welding line energy; A welding process quality score is determined according to the working parameters, the real-time equipment working state vector and the standard equipment working state vector.
3. The method for detecting welding quality according to claim 2, It is characterized in that Determining a welding process quality score according to the working parameters, the real-time equipment working state vector and the standard equipment working state vector includes: According to the formula Determine the welding process quality score Wt, where max is the maximum value function, min is the minimum value function, if is the conditional function, Ss T is the preset similarity threshold, Cu k is the welding current at the kth moment of the working cycle, Av k is the arc voltage at the kth moment of the working cycle, Wle k is the welding line energy at the kth moment of the working cycle, is the real-time device working state vector at the kth moment of the working cycle, for The transposed vector of Cu T is the standard welding current, Av T is the standard arc voltage, Wle T is the standard welding line energy, is the working state vector of the standard equipment, K is the number of moments in the working cycle, k≤K, k and K are both positive integers.
4. The method for detecting welding quality according to claim 1, It is characterized in that Determining a weld quality score of a sample welded product according to the weld quality parameter and the weld image includes: In the weld image, identifying whether there is a crack in the weld by using an image detection model, and determining a crack identification result; In the weld image, identifying whether there is slag inclusion in the weld by using an image detection model, and determining a slag inclusion identification result; In the weld image, identifying whether there is a lack of fusion phenomenon in the weld by using an image detection model, and determining a lack of fusion identification result; In the weld image, identifying whether there is a lack of penetration phenomenon in the weld by using an image detection model, and determining a lack of penetration identification result; A weld quality score of the sample welded product is determined according to the crack identification result, the slag inclusion identification result, the lack of fusion identification result, the lack of penetration identification result and the weld quality parameter.
5. The method for detecting welding quality according to claim 4, It is characterized in that Determining a weld quality score of a sample welding product according to the crack identification result, the slag inclusion identification result, the lack of fusion identification result, the lack of penetration identification result and the weld quality parameter includes: According to the formula Determine the weld quality score W of the i-th sample welding product qi , where α 1 , α 2 , α 3 and α 4 is the preset weight, if is the conditional function, Ww i is the weld width of the i-th sample welding product, Ww T is the preset weld width threshold, Wr i is the weld reinforcement of the i-th sample welding product, Wr T is the preset weld height threshold, Tt i Calculate the weld thickness of the i-th sample welded product, Ff T is the preset weld formation factor threshold, Df i is the penetration depth of the ith sample welding product, Df T is the preset penetration threshold, Fl i is the crack identification result of the i-th sample welding product, Si i is the slag inclusion identification result of the i-th sample welding product, Lof i is the lack of fusion identification result of the i-th sample welding product, Lop i is the incomplete penetration identification result of the i-th sample welding product, or is the logical operator of "or".
6. The method for detecting welding quality according to claim 1, It is characterized in that Determining the welding strength quality score of the sample welding product according to the pressure data and the bending angle includes: determining a first ratio according to the bending angle and the pressure data; Determine a standard deviation of the first ratio according to the first ratios at multiple moments in the welding strength detection cycle; A welding strength quality score of the sample welding product is determined according to the pressure data, the bending angle and the standard deviation of the first ratio.
7. The method for detecting welding quality according to claim 6, It is characterized in that Determining a welding strength quality score of a sample welding product according to the pressure data, the bending angle and the standard deviation of the first ratio includes: According to the formula Determine the welding strength quality score Ws of the i-th sample welding product i , where β 1 , β 2 and β 3 is the preset weight, α p is the preset multiple, if is the conditional function, Ba i,j Pd is the bending angle of the i-th sample welding product at the j-th moment of the welding strength test cycle, i,j is the pressure data of the i-th sample welding product at the j-th moment of the welding strength test cycle, is the first ratio of the i-th sample welding product at the j-th moment of the welding strength detection cycle, is the standard deviation of the first ratio, Ba i,e is the bending angle of the i-th sample welding product at the end of the welding strength test cycle, Ba T is the preset bending angle threshold, Pd i,e is the pressure data of the i-th sample welding product at the end of the welding strength test cycle, Pd T is the preset pressure data threshold, m is the number of moments in the welding strength detection cycle, j≤m, and both j and m are positive integers.
8. The method for detecting welding quality according to claim 7, It is characterized in that Determining an overall welding quality score according to the welding process quality score, the weld quality score and the welding strength quality score includes: Determine the welding quality score of the i-th sample welding product by taking a weighted sum of the weld quality score of the i-th sample welding product and the welding strength quality score of the i-th sample welding product; Determine a qualified identification result of the i-th sample welding product according to the welding quality score of the i-th sample welding product and a set welding quality score threshold; Determine the number of sample welded products; According to the number of the sample welding products, the qualified identification results of each sample welding product are summed up to determine the overall qualified identification result; determining a second ratio according to the overall qualified identification result and the number of the sample welding products; An overall welding quality score is determined according to the second ratio and the welding process quality score.
9. A method for detecting welding quality, It is characterized in that include: A welding equipment module, used to collect working parameters of the welding equipment through sensor equipment at multiple moments in a working cycle, wherein the working parameters include: welding current, arc voltage and welding line energy; A welding process quality module, used to determine a welding process quality score according to the working parameters; A sampling module is used to sample all welding products in the current batch to obtain sample welding products; An appearance parameter module is used to obtain weld quality parameters of sample welding products, wherein the weld quality parameters include: weld width, weld excess height, weld calculated thickness and penetration depth; An image acquisition module, used to acquire a weld image of a sample welding product through an image acquisition device; A weld quality module, used to determine a weld quality score of a sample welded product according to the weld quality parameter and the weld image; A detection data module is used to apply uniformly increasing pressure to the sample welding product through the detection equipment at multiple moments in the welding strength detection cycle, and obtain the pressure data of the detection equipment and the bending angle of the sample welding product; A welding strength quality module, used to determine a welding strength quality score of a sample welding product according to the pressure data and the bending angle; An overall welding quality module, used to determine an overall welding quality score according to the welding process quality score, the weld quality score and the welding strength quality score; The quality inspection report module is used to generate a welding quality inspection report based on the overall welding quality score.
Citation Information
Patent Citations
Welding quality detection device and detection method thereof
CN108760819A
Welding quality detection method
CN117629738A
Cited By
Welding quality monitoring method and system for plastic liner welding machine
CN120219370A
A welding quality monitoring method and system of a plastic liner welding machine
CN120219370B
Defect identification method for steel pipe manufacturing
CN120948617A
A method for defect recognition in steel pipe manufacturing
CN120948617B
