A welding monitoring system based on artificial intelligence

Abstract

The present invention relates to the field of welding monitoring technology, and in particular to a welding monitoring system based on artificial intelligence, comprising: a data acquisition module for collecting welding parameters, welding torch parameters and weldment parameters; a welding torch monitoring module for analyzing the running state of the welding torch; a penetration monitoring module for analyzing the abnormality of the penetration; an early warning module for analyzing the welding state and providing a user with an abnormal welding state early warning according to the analysis result; a current monitoring module for monitoring the state of the welding current and constructing an abnormal welding current coefficient; a temperature monitoring module for constructing an abnormal welding temperature coefficient; a quality monitoring module for analyzing the welding quality state according to the abnormal welding state early warning result, the welding current abnormal coefficient and the welding temperature abnormal coefficient within the monitoring period, and providing a user with an abnormal welding quality state alarm according to the analysis result. The present invention improves the welding monitoring efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of welding monitoring, and in particular to a welding monitoring system based on artificial intelligence. Background Art

[0002] In modern manufacturing, welding technology is widely used in the connection of various structures and components, especially in aerospace, automobile manufacturing and heavy industry. In these fields, welding quality directly affects the safety, reliability and economy of products. With the development of welding technology and the progress of materials science, the requirements for monitoring and quality assessment of welding process are also increasing.

[0003] Chinese Patent Publication No.: CN104741802A discloses a welding quality monitoring system and method, the system comprising: a welding gun, the welding gun is used to weld a welding spot; an infrared thermal imager, the infrared thermal imager is used to record the infrared thermal imaging data of the molten pool of the welding spot; an image acquisition card, the image acquisition card is used to acquire the infrared thermal imaging data of the molten pool, and send the infrared thermal imaging data of the molten pool to an image processing computer; an image processing computer, the image processing computer is used to analyze the infrared thermal imaging data of the molten pool to obtain welding parameters, compare the welding parameters with the preset welding standards, and obtain the welding spot quality evaluation results, so that the online monitoring of the automatic welding quality can be realized, the monitoring efficiency and quality are improved, and the missed detection rate is reduced; it can be seen that the scheme does not analyze the external environment (such as airflow, temperature and humidity) during the welding process, which may interfere with the collection of infrared thermal imaging data. At the same time, the delay of image processing may cause the inability to respond to the changes in welding parameters in time, and the relationship model between welding parameters and welding quality may lack universal applicability and cannot adapt to the diversity of different materials or processes. The scheme has the problems of low welding monitoring efficiency and low welding quality. Summary of the invention

[0004] The object of the present invention is to provide a welding monitoring system based on artificial intelligence to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] A welding monitoring system based on artificial intelligence, comprising:

[0007] A data acquisition module is used to collect welding parameters, welding torch parameters and weldment parameters;

[0008] The welding torch monitoring module is used to analyze the welding torch operation status according to the collected welding torch angle and welding torch position;

[0009] A penetration monitoring module is used to analyze the abnormality of the penetration depth based on the collected penetration depth;

[0010] An early warning module is used to analyze the welding state according to the analysis results of the welding torch operation state and the analysis results of the abnormality of the penetration depth, and to warn the user of abnormal welding state according to the analysis results;

[0011] The current monitoring module is used to monitor the state of the welding current according to the collected welding current, weldment thickness and weldment thermal conductivity during the monitoring period, and to construct the welding current abnormality coefficient;

[0012] The temperature monitoring module is used to construct the welding temperature anomaly coefficient according to the collected welding temperature and shielding gas flow rate;

[0013] The quality monitoring module is used to analyze the welding quality status according to the abnormal warning results of the welding status within the monitoring period, the construction results of the welding current abnormal coefficient and the welding temperature abnormal coefficient, and to issue an abnormal welding quality status alarm to the user according to the analysis results.

[0014] Furthermore, the welding torch monitoring module analyzes the abnormality of the welding torch angle according to the collected welding torch angle j0 and the preset angle j1, and the abnormality of the welding torch angle includes normal and abnormal;

[0015] The welding torch monitoring module analyzes the abnormality of the welding torch position according to the collected welding torch position z0 and the preset position z1, and the abnormality of the welding torch position includes normal and abnormal;

[0016] The welding torch monitoring module analyzes the welding torch operating status according to the analysis results of the welding torch angle abnormality and the welding torch position abnormality. If the welding torch angle is normal and the welding torch position is normal, the welding torch monitoring module determines that the welding torch operating status is normal. If the welding torch angle is abnormal or the welding torch position is abnormal, the welding torch monitoring module determines that the welding torch operating status is abnormal.

[0017] Furthermore, the penetration depth monitoring module analyzes the abnormality of the penetration depth according to the collected penetration depth r0 and the preset penetration depth r1, and the abnormality of the penetration depth includes normal and abnormal.

[0018] Furthermore, the warning module is used to analyze the welding state according to the analysis results of the welding torch operation state and the analysis results of the abnormality of the welding depth. The welding state includes normal and abnormal. If the welding state is abnormal, the user is warned of the abnormal welding state.

[0019] Further, the current monitoring module includes a current monitoring unit, a thickness analysis unit and a thermal conductivity analysis unit, and the current monitoring unit is used to compare the collected welding current c0 with each preset current to monitor the state of the welding current, and the state of the welding current includes normal and abnormal;

[0020] The current monitoring unit constructs a welding current abnormality coefficient HD according to an analysis result of the state of the welding current in a monitoring period.

[0021] Furthermore, the thickness analysis unit is used to compare the collected weld thickness h0 with the preset thickness h1 to analyze the abnormality of the weld thickness. The abnormality of the weld thickness includes normal and abnormal. If the weld thickness is abnormal, the first preset current is adjusted to c1', and the second preset current is adjusted to c2'.

[0022] Furthermore, the thermal conductivity analysis unit is used to compare the collected thermal conductivity r0 of the weld with the preset thermal conductivity r1 to analyze the abnormality of the thermal conductivity of the weld. The abnormality of the thermal conductivity of the weld includes normal and abnormal. If the thermal conductivity of the weld is abnormal, the preset thickness is adjusted to h1'.

[0023] Further, the temperature monitoring module includes a temperature monitoring unit, a flow monitoring unit and a temperature state analysis unit, wherein the temperature monitoring unit is used to compare the collected welding temperature t0 with the preset temperature t1, and analyze the abnormality of the welding temperature according to the comparison result, and the abnormality of the welding temperature includes normal and abnormal;

[0024] The flow monitoring unit is used to analyze the abnormality of the shielding gas flow according to the analysis result of the abnormality of the welding temperature and the collected shielding gas flow v0, and the abnormality of the shielding gas flow includes normal and abnormal;

[0025] The temperature state analysis unit is used to construct a welding temperature anomaly coefficient HT according to analysis results of welding temperature anomaly and shielding gas flow anomaly within a monitoring period.

[0026] Furthermore, the quality monitoring module includes a heat input state analysis unit and an alarm unit. The heat input state analysis unit is used to analyze the welding heat input state according to the construction results of the welding current abnormality coefficient and the welding temperature abnormality coefficient within the monitoring period. The welding heat input state includes normal and abnormal.

[0027] Furthermore, the alarm unit analyzes the welding quality status according to the abnormal warning results of the welding status and the analysis results of the welding heat input status during the monitoring period. The welding quality status includes normal and abnormal. If the welding heat input status is normal during the monitoring period, no alarm is issued; if the welding heat input status is abnormal during the monitoring period, an abnormal welding quality status alarm is issued to the user.

[0028] The beneficial effects of the present invention are as follows: the system effectively improves the stability and consistency of welding by accurately monitoring and adjusting factors such as the welding torch, penetration, current, temperature and gas flow, and promptly responds to potential problems through early warning and alarm mechanisms to ensure that all key parameters in the welding process are within a controllable range. Through the collaborative work of various modules, the automation level and quality control capability of the welding process are greatly improved, providing all-round technical support for high-demand manufacturing scenarios such as aerospace. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 Schematic diagram of the structure of the welding monitoring system based on artificial intelligence in this embodiment.

[0031] Figure 2 Schematic diagram of the structure of the current monitoring module of this embodiment.

[0032] Figure 3 Schematic diagram of the structure of the temperature monitoring module of this embodiment.

[0033] Figure 4 Schematic diagram of the structure of the quality monitoring module of this embodiment. DETAILED DESCRIPTION

[0034] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0035] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0036] See also Figure 1 As shown, it is a structural schematic diagram of the welding monitoring system based on artificial intelligence in this embodiment, and the system includes:

[0037] A data acquisition module is used to collect welding parameters, welding torch parameters and weldment parameters, wherein the welding parameters include welding current, welding temperature, penetration depth and shielding gas flow rate, the weldment parameters include weldment thickness and weldment thermal conductivity, the welding torch parameters include welding torch position and welding torch angle, the welding torch position is the straight-line distance between the welding torch and the weldment, and the welding torch angle is the inclination angle of the welding torch; in this embodiment, no specific limitation is made on the collection method of welding parameters, welding torch parameters and weldment parameters, and those skilled in the art can freely set them, as long as the collection requirements of welding parameters, welding torch parameters and weldment parameters are met, wherein the welding current can be collected by a current sensor, the welding temperature can be collected by a thermocouple, the penetration depth can be collected by a laser ranging sensor or a laser-based three-dimensional scanning device, the shielding gas flow rate can be collected by a flowmeter, the weldment thickness can be collected by an ultrasonic thickness gauge, the thermal conductivity of the weldment can be collected interactively, the welding torch position can be collected by a laser displacement sensor, and the welding torch angle can be collected by a tilt sensor.

[0038] Please continue reading Figure 1 As shown, the system includes a welding torch monitoring module, which is connected to the data acquisition module. The welding torch monitoring module is used to analyze the welding torch operation status according to the collected welding torch angle and welding torch position, and improve the analysis accuracy of the welding torch operation status by integrating the welding torch angle and the welding torch position, wherein:

[0039] The welding torch monitoring module analyzes the abnormality of the welding torch angle according to the collected welding torch angle j0 and the preset angle j1. If |j0-j1| / j1≤u1, the welding torch monitoring module determines that the welding torch angle is normal. If |j0-j1| / j1>u1, the welding torch monitoring module determines that the welding torch angle is abnormal.

[0040] The welding torch monitoring module analyzes the abnormality of the welding torch position according to the collected welding torch position z0 and the preset position z1. If |z0-z1| / z1≤u2, the welding torch monitoring module determines that the welding torch position is normal. If |z0-z1| / z1>u2, the welding torch monitoring module determines that the welding torch position is abnormal. u1 is the first offset coefficient and u2 is the second offset coefficient.

[0041] The welding torch monitoring module analyzes the operating status of the welding torch according to the analysis results of the abnormality of the welding torch angle and the abnormality of the welding torch position. If the welding torch angle is normal and the welding torch position is normal, the welding torch monitoring module determines that the operating status of the welding torch is normal. If the welding torch angle is abnormal or the welding torch position is abnormal, the welding torch monitoring module determines that the operating status of the welding torch is abnormal. By real-time monitoring the angle and position of the welding torch, welding defects caused by improper welding torch posture, such as incomplete penetration, inconsistent gaps, etc., can be effectively avoided, especially the high-precision requirements in the welding of thin-walled parts are guaranteed, thereby improving the welding monitoring efficiency.

[0042] It can be understood that, in the present embodiment, there is no specific limitation on the setting of the preset angle, preset position, the first offset coefficient and the second offset coefficient, and those skilled in the art can set them freely as long as the setting requirements of the preset angle, preset position, the first offset coefficient and the second offset coefficient are met. Among them, when the welding torch type is TIG, the optimal value of j1 is 15°, the optimal value of z1 is 2mm, the optimal value of u1 is 0.05, and the optimal value of u2 is 0.03.

[0043] Please continue reading Figure 1 As shown, the system includes a penetration monitoring module, which is connected to the data acquisition module. The penetration monitoring module analyzes the abnormality of the penetration according to the collected penetration r0 and the preset penetration r1. If |r0-r1|≤u3, the penetration monitoring module determines that the penetration is normal. If |r0-r1|>u3, the penetration monitoring module determines that the penetration is abnormal, and u3 is a third offset coefficient. By continuously monitoring the welding penetration, it is ensured that the weld has sufficient mechanical strength and welding integrity. By setting the third offset coefficient, the accuracy of the penetration abnormality analysis is improved, thereby improving the accuracy of the welding state analysis.

[0044] It can be understood that the present embodiment does not specifically limit the setting of the preset penetration depth and the third offset coefficient, and those skilled in the art can freely set them as long as the setting requirements of the preset penetration depth and the third offset coefficient are met. Among them, when the weldment is a thin-walled titanium alloy, the optimal value of r1 is 0.5 mm, and the optimal value of u3 is 0.08.

[0045] Please continue reading Figure 1 As shown, the system includes an early warning module, which is connected to the welding torch monitoring module and the penetration monitoring module. The early warning module is used to analyze the welding state according to the analysis results of the welding torch operation state and the analysis results of the abnormal penetration, and to warn the user of abnormal welding state according to the analysis results, wherein:

[0046] If the welding torch is in normal operation and the penetration depth is normal, the warning module determines that the welding state is normal and does not issue a warning;

[0047] If the welding torch operating state is abnormal or the penetration depth is abnormal, the early warning module determines that the welding state is abnormal and warns the user of the abnormal welding state. By monitoring the welding torch state and penetration depth and issuing abnormal warnings to the operator in a timely manner, welding defects can be avoided in advance, ensuring the stability of the welding process and thereby improving the welding monitoring efficiency.

[0048] Please continue reading Figure 1As shown, the system includes a current monitoring module, which is used to monitor the state of the welding current according to the welding current, weldment thickness and weldment thermal conductivity collected during the monitoring period, and to construct a welding current abnormality coefficient. The current abnormality coefficient is used to quantify the abnormal state of the welding current to improve the analysis efficiency of the abnormal state of the welding current. The current monitoring module is connected to the data acquisition module.

[0049] It is understandable that the present embodiment does not specifically limit the setting of the monitoring period, and those skilled in the art may freely set it as long as the setting requirements of the monitoring period are met, wherein the monitoring period may be set to 10 seconds, 20 seconds, etc.

[0050] See also Figure 2 As shown, the current monitoring module includes a current monitoring unit, which is used to compare the collected welding current c0 with each preset current to monitor the state of the welding current, wherein:

[0051] If c0<c1 or c0>c2, the current monitoring unit determines that the state of the welding current is abnormal;

[0052] If c1≤c0≤c2, the current monitoring unit determines that the state of the welding current is normal, c1 is the first preset current, c2 is the second preset current, and c1<c2;

[0053] The current monitoring unit constructs a welding current anomaly coefficient HD according to the analysis result of the welding current state within the monitoring period, and uses the welding current anomaly coefficient to quantify the abnormal state of the welding current, and sets HD=i1 / i0, i1 is the duration of the abnormal state of the welding current within the monitoring period, and i0 is the duration of the monitoring period; by real-time monitoring of the welding current, ensuring that the current is within the set range, and by monitoring the current and comparing it with the preset upper and lower limits, the welding defects caused by the abnormal current can be greatly reduced, especially when dealing with complex thin-walled parts and high-temperature alloy materials, so that the heat input is more stable and the welding consistency is better.

[0054] It can be understood that the present embodiment does not specifically limit the setting of each preset current, and those skilled in the art can freely set it as long as the setting requirements of each preset current are met. Among them, when the weldment is titanium alloy, the optimal value of c1 is 40A, and the optimal value of c2 is 50A.

[0055] Please continue reading Figure 2 As shown, the current monitoring module includes a thickness analysis unit, which is connected to the current monitoring unit. The thickness analysis unit is used to compare the collected weldment thickness h0 with the preset thickness h1 to analyze the abnormality of the weldment thickness, and adjust the state monitoring process of the welding current according to the analysis result to ensure that the welding current can be adjusted corresponding to different weldment thicknesses, wherein:

[0056] If h0≤h1, the thickness analysis unit determines that the thickness of the weldment is normal and no adjustment is made;

[0057] If h0>h1, the thickness analysis unit determines that the weld thickness is abnormal, and adjusts the first preset current to c1', setting: c1'=c1×{1+α×exp[3×(h0-h1) / (h0+h1)-3]}, and adjusts the second preset current to c2', setting c2'=c2×{1+α×exp[3×(h0-h1) / (h0+h1)-3]}, α is the preset adjustment ratio; by monitoring the weld thickness to adjust the set upper and lower limits of the current, it is ensured that the welding current can be adjusted to correspond to different weld thicknesses. This adjustment mechanism improves the accuracy of the weld current abnormality analysis.

[0058] It can be understood that the setting of the preset thickness and the preset adjustment ratio is not specifically limited in this embodiment, and those skilled in the art can set them freely as long as the setting requirements of the preset thickness and the preset adjustment ratio are met, where the optimal value of h1 is 1 mm, and the optimal value of α is 0.2.

[0059] Please continue reading Figure 2 As shown, the current monitoring module includes a thermal conductivity analysis unit, which is connected to the thickness analysis unit. The thermal conductivity analysis unit is used to compare the collected thermal conductivity r0 of the weld with the preset thermal conductivity r1 to analyze the abnormality of the thermal conductivity of the weld, and adjust the analysis process of the abnormality of the thickness of the weld according to the analysis result, so as to adjust the welding thickness threshold according to the change of thermal conductivity, wherein:

[0060] If r0≤r1, the thermal conductivity analysis unit determines that the thermal conductivity of the weldment is normal and does not make any adjustments;

[0061] If r0>r1, the thermal conductivity analysis unit determines that the thermal conductivity of the weldment is abnormal, and adjusts the preset thickness to h1', setting:

[0062] h1'=h1×{1-ln[4×(r0-r1) / (r1+r0)+1] / ln5}; By accurately monitoring the thermal conductivity of the welding material, the thickness parameters of the weldment are adjusted according to the change in thermal conductivity to prevent welding quality problems caused by differences in material thermal conductivity, thereby improving welding monitoring efficiency.

[0063] It can be understood that the setting of the preset thermal conductivity is not specifically limited in this embodiment, and those skilled in the art can set it freely as long as the setting requirements of the preset thermal conductivity are met. Among them, when the weldment is titanium alloy, the optimal value of r1 is 6.6 W / (m·K).

[0064] Please continue reading Figure 1 As shown, the system includes a temperature monitoring module, which is connected to the data acquisition module. The temperature monitoring module is used to construct a welding temperature anomaly coefficient according to the collected welding temperature and protective gas flow rate, and use the welding temperature anomaly coefficient to quantify the abnormal state of the welding temperature.

[0065] See also Figure 3 As shown, the temperature monitoring module includes a temperature monitoring unit, which is used to compare the collected welding temperature t0 with the preset temperature t1, and analyze the abnormality of the welding temperature according to the comparison result, wherein:

[0066] If t0≤t1, the temperature monitoring unit determines that the welding temperature is normal;

[0067] If t0>t1, the temperature monitoring unit determines that the welding temperature is abnormal.

[0068] It is understandable that the setting of the preset temperature is not specifically limited in this embodiment, and those skilled in the art can set it freely as long as the setting requirements of the preset temperature are met. Among them, when the weldment is titanium alloy, the optimal value of t1 is 1000°C.

[0069] Please continue reading Figure 3 As shown, the temperature monitoring module includes a flow monitoring unit, which is connected to the temperature monitoring unit. The flow monitoring unit is used to analyze the abnormality of the shielding gas flow according to the analysis result of the welding temperature abnormality and the collected shielding gas flow v0, so as to adopt different technical means for gas flow monitoring for different temperature environments, wherein:

[0070] When the welding temperature is normal, if v1≤v0≤v2, the flow monitoring unit determines that the flow of the shielding gas is normal; if v0<v1 or v0>v2, the flow monitoring unit determines that the flow of the shielding gas is abnormal;

[0071] When the welding temperature is abnormal, if v1×{1+exp[lg(t0-t1) / t1]}≤v0≤v2×{1+exp[lg(t0-t1) / t1]}, the flow monitoring unit determines that the shielding gas flow is normal; if v0<v1×{1+exp[lg(t0-t1) / t1]} or v0>v2×{1+exp[lg(t0-t1) / t1]}, the flow monitoring unit determines that the shielding gas flow is abnormal, v1 is the first preset flow, v2 is the second preset flow, and v1<v2; by monitoring the shielding gas flow, the gas flow is accurately controlled and closed-loop with the welding temperature in real time to ensure that the flow change is within a reasonable range, thereby avoiding welding defects and improving the welding monitoring efficiency.

[0072] It can be understood that the present embodiment does not specifically limit the setting of each preset flow rate, and those skilled in the art can freely set it as long as the setting requirements of each preset flow rate are met. Among them, when the weldment is titanium alloy, the optimal value of v1 is 16L / min, and the optimal value of v2 is 21L / min.

[0073] Please continue reading Figure 3 As shown, the temperature monitoring module includes a temperature state analysis unit, which is connected to the flow monitoring unit. The temperature state analysis unit is used to construct a welding temperature anomaly coefficient HT according to the analysis results of welding temperature anomaly and shielding gas flow anomaly in the monitoring period, and set HT=(x1×i2 / i0+x2×i3 / i0) / T; the welding temperature anomaly state is analyzed by comprehensively analyzing the analysis results of welding temperature and shielding gas flow anomaly, thereby improving the accuracy of welding temperature anomaly coefficient construction, thereby improving the accuracy of welding quality state analysis, and finally improving welding monitoring efficiency;

[0074] Among them, x1 is the temperature weight, x2 is the flow weight, x1+x2=1, x1>x2, T is the preset temperature state threshold, i2 is the duration of abnormal welding temperature during the monitoring period, and i3 is the duration of abnormal shielding gas flow during the monitoring period.

[0075] It can be understood that in this embodiment, there is no specific limitation on the setting of temperature weight, flow weight and preset temperature state threshold. Those skilled in the art can set them freely as long as the setting requirements of temperature weight, flow weight and preset temperature state threshold are met. Among them, the best value of x1 is 0.7, the best value of x2 is 0.3, and the best value of T is 0.6.

[0076] Please continue reading Figure 1 As shown, the system includes a quality monitoring module, which is connected to the early warning module, the current monitoring module, and the temperature monitoring module. The quality monitoring module is used to analyze the welding quality status according to the abnormal early warning results of the welding status within the monitoring period, the construction results of the welding current abnormal coefficient and the welding temperature abnormal coefficient, so as to achieve accurate analysis of the welding quality status, improve the consistency of the welding quality status analysis, and issue an abnormal welding quality status alarm to the user according to the analysis results.

[0077] See also Figure 4 As shown, the quality monitoring module includes a heat input state analysis unit, which is used to analyze the welding heat input state according to the construction results of the welding current abnormal coefficient and the welding temperature abnormal coefficient in the monitoring period, and to construct a heat input state index by analyzing the current and temperature state during the welding process to ensure the balance of heat input during the welding process, wherein:

[0078] If h1×HD+h2×HT≤γ, the heat input state analysis unit determines that the welding heat input state of the current monitoring period is normal;

[0079] If h1×HD+h2×HT>γ, the heat input state analysis unit determines that the welding heat input state in the current monitoring period is abnormal; through accurate heat input monitoring, the welding performance is effectively improved to ensure that the material in the welding area can meet the strength requirements while avoiding excessive hardening of the weld or changes in the heat-affected zone, thereby improving the accuracy of welding quality state analysis and thus improving welding monitoring efficiency;

[0080] Among them, h1 is the current weight, h2 is the temperature weight, h1+h2=1, and γ is the heat input state coefficient.

[0081] It can be understood that, in this embodiment, there is no specific limitation on the setting of the current weight, temperature weight and heat input state coefficient, and those skilled in the art can set them freely as long as the setting requirements of the current weight, temperature weight and heat input state coefficient are met. Among them, the optimal value of h1 is 0.45, the optimal value of h2 is 0.55, and the optimal value of γ is 0.26.

[0082] Please continue reading Figure 4 As shown, the quality monitoring module includes an alarm unit, which is connected to the heat input state analysis unit. The alarm unit analyzes the welding quality state according to the abnormal welding state warning result and the analysis result of the welding heat input state within the monitoring period, and issues an abnormal welding quality state alarm to the user according to the analysis result, wherein:

[0083] If the welding heat input state is normal during the monitoring period, when YC / i0≤η, the alarm unit determines that the welding quality state of the current monitoring period is normal and does not issue an alarm; when YC / i0>η, the alarm unit determines that the welding quality state of the current monitoring period is abnormal and issues an abnormal welding quality state alarm to the user;

[0084] If the welding heat input state is abnormal during the monitoring period, the alarm unit determines that the welding quality state of the current monitoring period is abnormal, and issues an abnormal welding quality state alarm to the user; based on the heat input state and the welding early warning results, the welding quality is comprehensively analyzed and an alarm is issued. In particular, for key components such as thin-walled components in aerospace engines, any abnormality in the welding process will affect the final quality. When the alarm unit finds that the welding heat input is too high or there is a welding quality problem, it can promptly notify the operator to prevent the continuation of unqualified welding operations due to ignoring abnormal details, thereby ensuring the integrity and consistency of welding and improving the efficiency of welding monitoring;

[0085] Among them, YC is the duration of abnormal warning of welding status within the monitoring period, and η is the preset abnormal proportion.

[0086] It can be understood that in this implementation, the setting of the preset abnormality ratio is not specifically limited, and those skilled in the art can freely set it as long as the setting requirements of the preset abnormality ratio are met, wherein the optimal value of η is 0.05.

[0087] Specifically, the system described in this embodiment is applied to the monitoring of welding of thin-walled parts in jet engines in the aerospace field. By analyzing the welding status and welding quality status and providing timely warnings to users, the welding monitoring efficiency is improved.

[0088] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the embodiments here. All obvious changes or modifications derived from the technical solution of the present invention are still within the protection scope of the present invention.

Claims

1. A welding monitoring system based on artificial intelligence, characterized in that: include: A data acquisition module, used to collect welding parameters, welding torch parameters and weldment parameters; The welding torch monitoring module is used to analyze the welding torch operation status according to the collected welding torch angle and welding torch position; A penetration monitoring module is used to analyze the abnormality of the penetration depth based on the collected penetration depth; An early warning module is used to analyze the welding state according to the analysis results of the welding torch operation state and the analysis results of the abnormality of the welding depth, and to warn the user of abnormal welding state according to the analysis results; The current monitoring module is used to monitor the state of the welding current according to the collected welding current, weldment thickness and weldment thermal conductivity during the monitoring period, and to construct the welding current abnormality coefficient; The temperature monitoring module is used to construct the welding temperature anomaly coefficient according to the collected welding temperature and shielding gas flow rate; The quality monitoring module is used to analyze the welding quality status according to the abnormal warning results of the welding status within the monitoring period, the construction results of the welding current abnormal coefficient and the welding temperature abnormal coefficient, and to warn the user of the abnormal welding quality status according to the analysis results; The current monitoring module includes a current monitoring unit, a thickness analysis unit and a thermal conductivity analysis unit. The current monitoring unit is used to compare the collected welding current c0 with each preset current to monitor the state of the welding current. The state of the welding current includes normal and abnormal. The current monitoring unit constructs a welding current abnormality coefficient HD according to the analysis result of the welding current state in the monitoring period, and sets HD=i1 / i0, i1 is the duration of the welding current state abnormality in the monitoring period, and i0 is the duration of the monitoring period; The thickness analysis unit is used to compare the collected weld thickness h0 with the preset thickness h1 to analyze the abnormality of the weld thickness. The abnormality of the weld thickness includes normal and abnormal. If the weld thickness is abnormal, the first preset current is adjusted to c1', and the setting is: c1'=c1×{1+α×exp[3×(h0-h1) / (h0+h1)-3]}, and the second preset current is adjusted to c2' and the setting is c2'=c2×{1+α×exp[3×(h0-h1) / (h0+h1)-3]}, α is the preset adjustment ratio, c1 is the first preset current, and c2 is the second preset current; The thermal conductivity analysis unit is used to compare the collected thermal conductivity r0 of the weld with the preset thermal conductivity r1 to analyze the abnormality of the thermal conductivity of the weld. The abnormality of the thermal conductivity of the weld includes normal and abnormal. If the thermal conductivity of the weld is abnormal, the preset thickness is adjusted to h1', and it is set: h1'=h1×{1-ln[4×(r0-r1) / (r1+r0)+1] / ln5}.

2. The welding monitoring system based on artificial intelligence according to claim 1 is characterized in that: The welding torch monitoring module analyzes the abnormality of the welding torch angle according to the collected welding torch angle j0 and the preset angle j1, and the abnormality of the welding torch angle includes normal and abnormal; The welding torch monitoring module analyzes the abnormality of the welding torch position according to the collected welding torch position z0 and the preset position z1, and the abnormality of the welding torch position includes normal and abnormal; The welding torch monitoring module analyzes the welding torch operating status according to the analysis results of the welding torch angle abnormality and the welding torch position abnormality. If the welding torch angle is normal and the welding torch position is normal, the welding torch monitoring module determines that the welding torch operating status is normal. If the welding torch angle is abnormal or the welding torch position is abnormal, the welding torch monitoring module determines that the welding torch operating status is abnormal.

3. The welding monitoring system based on artificial intelligence according to claim 2 is characterized in that: The penetration depth monitoring module analyzes the abnormality of the penetration depth according to the collected penetration depth rs0 and the preset penetration depth rs1, and the abnormality of the penetration depth includes normal and abnormal.

4. The welding monitoring system based on artificial intelligence according to claim 3 is characterized in that: The early warning module is used to analyze the welding state according to the analysis results of the welding torch operation state and the analysis results of the abnormality of the welding depth. The welding state includes normal and abnormal. If the welding state is abnormal, an abnormal welding state early warning is issued to the user.

5. The welding monitoring system based on artificial intelligence according to claim 4 is characterized in that: The temperature monitoring module includes a temperature monitoring unit, a flow monitoring unit and a temperature state analysis unit. The temperature monitoring unit is used to compare the collected welding temperature t0 with the preset temperature t1, and analyze the abnormality of the welding temperature according to the comparison result. The abnormality of the welding temperature includes normal and abnormal. The flow monitoring unit is used to analyze the abnormality of the shielding gas flow according to the analysis result of the abnormality of the welding temperature and the collected shielding gas flow v0, and the abnormality of the shielding gas flow includes normal and abnormal; The temperature state analysis unit is used to construct a welding temperature anomaly coefficient HT according to analysis results of welding temperature anomaly and shielding gas flow anomaly within a monitoring period.

6. The welding monitoring system based on artificial intelligence according to claim 5 is characterized in that: The quality monitoring module includes a heat input state analysis unit and an alarm unit. The heat input state analysis unit is used to analyze the welding heat input state according to the construction results of the welding current abnormal coefficient and the welding temperature abnormal coefficient within the monitoring period. The welding heat input state includes normal and abnormal.

7. The welding monitoring system based on artificial intelligence according to claim 6 is characterized in that: The alarm unit analyzes the welding quality status according to the abnormal welding status warning result and the analysis result of the welding heat input status within the monitoring period. The welding quality status includes normal and abnormal. If the welding heat input status is normal within the monitoring period, no alarm is issued; if the welding heat input status is abnormal within the monitoring period, an abnormal welding quality status alarm is issued to the user.

Images