Welding quality monitoring system based on real-time acquisition and dynamic analysis

Abstract

A welding quality monitoring system based on real-time acquisition and dynamic analysis includes: a real-time data acquisition module, which uses a high-speed, high-precision data acquisition card to acquire current and voltage data during the welding process in real time at a sampling frequency of milliseconds; and a dynamic data analysis module, which uses deep learning algorithms and big data analysis to perform real-time and accurate analysis on the acquired current and voltage fluctuation signals in order to quickly identify various abnormal information during the welding process.

Description

Technical Field

[0001] This invention relates to a welding quality monitoring system based on real-time acquisition and dynamic analysis. Background Technology

[0002] Welding, as a fundamental and crucial process, is widely used in many fields such as construction, machinery manufacturing, automotive industry, and aerospace. However, traditional welding equipment has many drawbacks, which seriously restrict the efficiency and quality improvement of welding operations. Therefore, welding robots have emerged to replace traditional welding equipment and improve the efficiency and quality of welding operations.

[0003] In the process of monitoring welding quality, most judgments rely on human experience, lacking real-time and accurate data acquisition and analysis methods. Fluctuations in key parameters such as current and voltage are often difficult to detect in time, resulting in welding defects not being discovered and corrected in the early stages. At the same time, due to the lack of a complete process data recording system, it is difficult to trace various parameters in the welding process once welding quality problems occur, which is not conducive to process optimization and improvement. Summary of the Invention

[0004] This invention provides a welding quality monitoring system based on real-time acquisition and dynamic analysis. With a rational structural design, it utilizes the combined action of a real-time data acquisition module and a dynamic data analysis module to collect current and voltage data during the welding process at a millisecond-level sampling frequency. Employing deep learning algorithms and big data analytics, it performs real-time and precise analysis of the acquired current and voltage fluctuation signals, enabling rapid identification of various abnormalities during the welding process. Simultaneously, it automatically selects and records the coordinates of abnormal points for subsequent in-depth analysis of the causes, pauses the welding operation, and issues a shutdown warning. This allows for real-time and accurate monitoring of welding quality, timely detection and handling of welding abnormalities, prevention of defect expansion, and ensures the stability and reliability of welding quality, improving product qualification rates and solving problems existing in the prior art.

[0005] The technical solution adopted by the present invention to solve the above-mentioned technical problems is as follows:

[0006] A welding quality monitoring system based on real-time data acquisition and dynamic analysis, the monitoring system comprising:

[0007] The real-time data acquisition module is used to acquire current and voltage data during the welding process in real time at a sampling frequency of milliseconds using a high-speed, high-precision data acquisition card.

[0008] The data dynamic analysis module is used to perform real-time and accurate analysis of the collected current and voltage fluctuation signals using deep learning algorithms and big data analysis, so as to quickly identify various abnormal information in the welding process.

[0009] The monitoring method of the monitoring system includes the following steps:

[0010] S1, set the weighting coefficient and influence ratio of DC gas shielded welding;

[0011] S2, set the weighting coefficient and influence ratio of pulse gas shielded welding;

[0012] S3, calculate the corresponding reference frequency;

[0013] S4, calculate the corresponding defect tendency rate.

[0014] The weighting coefficients for DC gas shielded welding and pulsed gas shielded welding both include current deviation, voltage deviation, power deviation, current frequency deviation, voltage frequency deviation, and power frequency deviation.

[0015] The current deviation is used to determine the welding wire melting speed and penetration depth; the voltage deviation is used to control the arc length and energy distribution; the power deviation is used to comprehensively reflect the heat input; the current frequency deviation is used to determine the droplet transition frequency and heat input distribution; the voltage frequency deviation is used to affect the arc stability; and the power frequency deviation is used to indirectly affect the periodic fluctuations of the heat input.

[0016] For the weighting coefficients of DC gas shielded welding, the influence of current deviation is 40%, the influence of voltage deviation is 30%, the influence of power deviation is 15%, the influence of current frequency deviation is 8%, the influence of voltage frequency deviation is 5%, and the influence of power frequency deviation is 2%.

[0017] For the weighting coefficients of pulsed gas shielded welding, the influence of current deviation is 25%, the influence of voltage deviation is 20%, the influence of power deviation is 15%, the influence of current frequency deviation is 15%, the influence of voltage frequency deviation is 10%, and the influence of power frequency deviation is 15%.

[0018] Calculating the corresponding reference frequency involves the following steps:

[0019] S3.1, the short-circuit transition frequency is calculated using the wire feed speed and arc voltage; the calculation formula is as follows:

[0020] Short-circuit transition frequency = wire feed speed / (arc length + short-circuit burn-back length) × welding wire diameter;

[0021] S3.2, Determine the current frequency and voltage frequency based on the pulse transition frequency of the welding robot;

[0022] S3.3, set the current to I s The voltage is set to U.s The frequency is set to P. s Set the pulse transition frequency to G. s The reference frequency F is obtained through the relation coefficient. r =θ(U S I s G S ).

[0023] Let I be the real-time current of the welding robot at time t during the welding process. a (t), real-time voltage is U a (t), real-time power is P a (t); combined with the calculated current frequency F I (t), voltage frequency F U (t) and power frequency F P The defect tendency rate δ(t) is obtained as follows:

[0024] ,

[0025] Where a, b, c, d, e, g are weighting coefficients.

[0026] The monitoring system can record various data during the welding process in real time at 100ms intervals, including current, voltage, oscillation frequency, oscillation amplitude, and welding speed. It can obtain the trajectory path information of the welding operation task by interacting with the motion control system of the navigation wheeled mobile platform and the industrial robotic arm. The data is organized according to time sequence and task number and stored in solid-state drive to establish a dual indexing mechanism based on time sequence and task number.

[0027] The navigation wheeled mobile platform is equipped with high-precision laser navigation and visual navigation functions, and is equipped with a path planning algorithm. In actual working scenarios, the welding robot first scans the surrounding environment with LiDAR to build a map model, and then combines the image information obtained by the visual sensor to identify obstacles and target positions in the work area in real time. According to the preset task instructions and map information, the path planning algorithm automatically generates the optimal movement path, controls the navigation wheeled mobile platform to move to the designated work position at a stable speed and in a precise direction, and ensures that the robot can operate efficiently and safely in complex working environments.

[0028] The load capacity, repeatability, joint angle, movement speed, and acceleration of the industrial robotic arm can all be adjusted to achieve precise motion control.

[0029] The monitoring system can establish a stable communication connection with the MES system via Ethernet or wireless local area network. When the MES system issues a work task scheduling instruction, the system first parses and verifies the received instruction to ensure its accuracy and completeness. Then, according to the instruction content, it controls the navigation wheeled mobile platform to move to the designated workstation, while simultaneously adjusting the industrial robotic arm to a specific posture and parking position. It receives and parses the robot operation program from the MES system, sends the program parameters to the control systems of the welding system and the industrial robotic arm, and starts and executes the operation program. During the operation, it provides real-time feedback to the MES system on the robot's working status and task progress, realizing real-time monitoring and management of the production process.

[0030] This invention employs the aforementioned structure, utilizing a high-speed, high-precision data acquisition card in a real-time data acquisition module to collect current and voltage data during the welding process at a millisecond-level sampling frequency. A dynamic data analysis module, employing deep learning algorithms and big data analysis, performs real-time and precise analysis of the acquired current and voltage fluctuation signals to quickly identify various anomalies during the welding process. Through the analysis and mining of a large amount of welding process data, it is possible to gain a deeper understanding of the impact of various factors on welding quality, thereby optimizing welding process parameters and improving production efficiency. A high-capacity, high-reliability solid-state drive is used as the data storage medium to record key information such as current, voltage, oscillation frequency, oscillation amplitude, and welding speed during the welding process in real time. By establishing a unique data index and association mechanism, this information is precisely correlated with the trajectory path of the welding task, offering advantages of precision, efficiency, stability, and practicality. Attached Figure Description

[0031] Figure 1 This is a schematic diagram of the structure of the present invention.

[0032] Figure 2 This is a schematic diagram of the process of the present invention. Detailed Implementation

[0033] To clearly illustrate the technical features of this solution, the invention will be described in detail below through specific implementation methods and in conjunction with the accompanying drawings.

[0034] like Figure 1-2 As shown, the welding quality monitoring system is based on real-time acquisition and dynamic analysis. The monitoring system includes:

[0035] The real-time data acquisition module is used to acquire current and voltage data during the welding process in real time at a sampling frequency of milliseconds using a high-speed, high-precision data acquisition card.

[0036] The data dynamic analysis module is used to perform real-time and accurate analysis of the collected current and voltage fluctuation signals using deep learning algorithms and big data analysis, so as to quickly identify various abnormal information in the welding process.

[0037] The monitoring method of the monitoring system includes the following steps:

[0038] S1, set the weighting coefficient and influence ratio of DC gas shielded welding;

[0039] S2, set the weighting coefficient and influence ratio of pulse gas shielded welding;

[0040] S3, calculate the corresponding reference frequency;

[0041] S4, calculate the corresponding defect tendency rate.

[0042] The weighting coefficients for DC gas shielded welding and pulsed gas shielded welding both include current deviation, voltage deviation, power deviation, current frequency deviation, voltage frequency deviation, and power frequency deviation.

[0043] The current deviation is used to determine the welding wire melting speed and penetration depth; the voltage deviation is used to control the arc length and energy distribution; the power deviation is used to comprehensively reflect the heat input; the current frequency deviation is used to determine the droplet transition frequency and heat input distribution; the voltage frequency deviation is used to affect the arc stability; and the power frequency deviation is used to indirectly affect the periodic fluctuations of the heat input.

[0044] For the weighting coefficients of DC gas shielded welding, the influence of current deviation is 40%, the influence of voltage deviation is 30%, the influence of power deviation is 15%, the influence of current frequency deviation is 8%, the influence of voltage frequency deviation is 5%, and the influence of power frequency deviation is 2%.

[0045] For the weighting coefficients of pulsed gas shielded welding, the influence of current deviation is 25%, the influence of voltage deviation is 20%, the influence of power deviation is 15%, the influence of current frequency deviation is 15%, the influence of voltage frequency deviation is 10%, and the influence of power frequency deviation is 15%.

[0046] Calculating the corresponding reference frequency involves the following steps:

[0047] S3.1, the short-circuit transition frequency is calculated using the wire feed speed and arc voltage; the calculation formula is as follows:

[0048] Short-circuit transition frequency = wire feed speed / (arc length + short-circuit burn-back length) × welding wire diameter;

[0049] S3.2, Determine the current frequency and voltage frequency based on the pulse transition frequency of the welding robot;

[0050] S3.3, set the current to I s The voltage is set to U. s The frequency is set to P. s Set the pulse transition frequency to G. s The reference frequency F is obtained through the relation coefficient. r =θ(U S I s G S ).

[0051] Let I be the real-time current of the welding robot at time t during the welding process. a (t), real-time voltage is U a (t), real-time power is P a (t); combined with the calculated current frequency F I (t), voltage frequency F U (t) and power frequency F P The defect tendency rate δ(t) is obtained as follows:

[0052] ,

[0053] Where a, b, c, d, e, g are weighting coefficients.

[0054] The monitoring system can record various data during the welding process in real time at 100ms intervals, including current, voltage, oscillation frequency, oscillation amplitude, and welding speed. It can obtain the trajectory path information of the welding operation task by interacting with the motion control system of the navigation wheeled mobile platform and the industrial robotic arm. The data is organized according to time sequence and task number and stored in solid-state drive to establish a dual indexing mechanism based on time sequence and task number.

[0055] The navigation wheeled mobile platform is equipped with high-precision laser navigation and visual navigation functions, and is equipped with a path planning algorithm. In actual working scenarios, the welding robot first scans the surrounding environment with LiDAR to build a map model, and then combines the image information obtained by the visual sensor to identify obstacles and target positions in the work area in real time. According to the preset task instructions and map information, the path planning algorithm automatically generates the optimal movement path, controls the navigation wheeled mobile platform to move to the designated work position at a stable speed and in a precise direction, and ensures that the robot can operate efficiently and safely in complex working environments.

[0056] The load capacity, repeatability, joint angle, movement speed, and acceleration of the industrial robotic arm can all be adjusted to achieve precise motion control.

[0057] The monitoring system can establish a stable communication connection with the MES system via Ethernet or wireless local area network. When the MES system issues a work task scheduling instruction, the system first parses and verifies the received instruction to ensure its accuracy and completeness. Then, according to the instruction content, it controls the navigation wheeled mobile platform to move to the designated workstation, while simultaneously adjusting the industrial robotic arm to a specific posture and parking position. It receives and parses the robot operation program from the MES system, sends the program parameters to the control systems of the welding system and the industrial robotic arm, and starts and executes the operation program. During the operation, it provides real-time feedback to the MES system on the robot's working status and task progress, realizing real-time monitoring and management of the production process.

[0058] The working principle of the welding quality monitoring system based on real-time acquisition and dynamic analysis in this embodiment of the invention is as follows: Based on the cooperation of the real-time data acquisition module and the dynamic data analysis module, the current and voltage data during the welding process are acquired in real time at a sampling frequency of milliseconds. Using deep learning algorithms and big data analysis technology, the acquired current and voltage fluctuation signals are analyzed in real time and accurately. This allows for the rapid identification of various abnormal information during the welding process. At the same time, the system automatically selects and records the coordinates of abnormal points to facilitate in-depth analysis of the causes. The system can also pause the welding operation and issue a shutdown warning. Thus, the system can monitor welding quality in real time and accurately, promptly detect and handle welding abnormalities, prevent defects from expanding, ensure the stability and reliability of welding quality, and improve the product qualification rate.

[0059] In the overall solution, the monitoring system includes: a real-time data acquisition module, which uses a high-speed, high-precision data acquisition card to acquire current and voltage data during the welding process in real time at a sampling frequency of milliseconds; and a dynamic data analysis module, which uses deep learning algorithms and big data analysis to perform real-time and accurate analysis on the acquired current and voltage fluctuation signals in order to quickly identify various abnormal information in the welding process. Because in actual welding operations, the lack of real-time and accurate data acquisition and analysis methods makes it difficult to detect fluctuations in key parameters such as current and voltage in a timely manner, resulting in welding defects not being detected and corrected in the early stages. Therefore, the monitoring system of this application can accurately solve the above problems.

[0060] Correspondingly, the monitoring method of the monitoring system includes the following steps: setting the weighting coefficient and influence ratio of DC gas shielded welding; setting the weighting coefficient and influence ratio of pulsed gas shielded welding; calculating the corresponding reference frequency; and calculating the corresponding defect tendency rate.

[0061] Specifically, the weighting coefficients for DC gas shielded welding and pulsed gas shielded welding both include current deviation, voltage deviation, power deviation, current frequency deviation, voltage frequency deviation, and power frequency deviation.

[0062] The current deviation is used to determine the welding wire melting speed and penetration depth; the voltage deviation is used to control the arc length and energy distribution; the power deviation is used to comprehensively reflect the heat input; the current frequency deviation is used to determine the droplet transition frequency and heat input distribution; the voltage frequency deviation is used to affect arc stability; the power frequency deviation is used to indirectly affect the periodic fluctuation of heat input. For the weighted coefficient of DC gas shielded welding, the influence ratio of the current deviation is 40%, the influence ratio of the voltage deviation is 30%, the influence ratio of the power deviation is 15%, the influence ratio of the current frequency deviation is 8%, the influence ratio of the voltage frequency deviation is 5%, and the influence ratio of the power frequency deviation is 2%. For the weighted coefficient of pulsed gas shielded welding, the influence ratio of the current deviation is 25%, the influence ratio of the voltage deviation is 20%, the influence ratio of the power deviation is 15%, the influence ratio of the current frequency deviation is 15%, the influence ratio of the voltage frequency deviation is 10%, and the influence ratio of the power frequency deviation is 15%.

[0063] The current directly determines the melting speed and penetration depth of the welding wire; too high a current will cause the molten pool to overheat, increase spatter, and burn through; too low a current will cause incomplete fusion, insufficient penetration depth, and porosity; in pulse welding, current deviation will also disrupt the stability of droplet transfer, resulting in uneven weld or cracks.

[0064] Voltage controls the arc length and energy distribution; excessively high voltage will cause the arc to be too long, resulting in undercut and excessively wide welds; insufficient voltage will lead to an unstable arc, short circuit between the welding wire and the workpiece, causing spatter and porosity; the matching of voltage and current is crucial for heat input balance, and the superposition of deviations between the two will significantly increase the risk of defects.

[0065] Power, as the product of current and voltage, comprehensively reflects the heat input. Power deviation may be caused by deviations in current or voltage alone, and its effects manifest as fluctuations in the molten pool temperature, leading to overheating or uneven cooling, which in turn causes cracks, deformation, or structural defects.

[0066] Generally, since the dominant factors for specific defect types may differ, adjustments need to be made in conjunction with process conditions. In practical applications, parameter sensitivity needs to be verified through process evaluation, and weight allocation needs to be dynamically optimized.

[0067] Preferably, calculating the corresponding reference frequency includes the following steps: calculating the short-circuit transition frequency using wire feed speed and arc voltage; the calculation formula is: short-circuit transition frequency = wire feed speed / (arc length + short-circuit burn-back length) × welding wire diameter; determining the current frequency and voltage frequency based on the welding robot pulse transition frequency; setting the current as I. s The voltage is set to U. s The frequency is set to P. s Set the pulse transition frequency to G.s The reference frequency F is obtained through the relation coefficient. r =θ(U S I s G S ).

[0068] The pulse transition frequency is set by the welding robot, and the short-circuit transition frequency is set by the actual number of short circuits or by referring to the default parameters of the welding machine.

[0069] Regarding the defect tendency rate, the real-time current of the welding robot at time t during the welding process is set as I. a (t), real-time voltage is U a (t), real-time power is P a (t); combined with the calculated current frequency F I (t), voltage frequency F U (t) and power frequency F P The defect tendency rate δ(t) is obtained as follows:

[0070] ,

[0071] Where a, b, c, d, e, g are weighting coefficients.

[0072] Based on real-time collection of various electrical parameters, relevant data are calculated to accurately identify corresponding fluctuation signals. Combined with preset control strategies, the coordinates of abnormal points can be automatically selected and recorded, and shutdown warning measures can be taken directly to ensure the stability and reliability of welding quality.

[0073] Furthermore, the monitoring system can record various data during the welding process in real time at 100ms intervals, including current, voltage, oscillation frequency, oscillation amplitude, and welding speed. It can also interact with the motion control system of the navigation wheeled mobile platform and the industrial robotic arm to obtain the trajectory path information of the welding operation task. The data is organized according to time sequence and task number and stored in solid-state drive to establish a dual indexing mechanism based on time sequence and task number, which facilitates data query and traceability.

[0074] To improve the system's monitoring and control efficiency, the monitoring system can establish a stable communication connection with the MES system via Ethernet or a wireless local area network. When the MES system issues a work task scheduling instruction, the system first parses and verifies the received instruction to ensure its accuracy and completeness. Then, according to the instruction content, it controls the navigation wheeled mobile platform to move to the designated workstation, while simultaneously adjusting the industrial robotic arm to a specific posture and parking position. The system receives and parses the robot operation program from the MES system, sends the program parameters to the control systems of the welding system and the industrial robotic arm, and starts and executes the operation program. During the operation, the system provides real-time feedback to the MES system on the robot's working status and task progress, realizing real-time monitoring and management of the production process.

[0075] It should be noted that the monitoring system of this application can collect data at a sampling frequency of 2 kHz or higher and convert it into digital signals; use deep learning algorithms (such as convolutional neural networks) to extract features and recognize patterns from the digital signals; and determine whether there are any abnormalities in the welding process by comparing the data with the data model under normal welding conditions.

[0076] In this application, welding quality can be monitored in real time and accurately, welding abnormalities can be detected and dealt with in a timely manner, the detection rate of welding abnormalities can reach more than 95%, measures can be taken in the early stage of welding defects to avoid the expansion of defects, and the product qualification rate can be improved.

[0077] In summary, the welding quality monitoring system based on real-time acquisition and dynamic analysis in this embodiment of the invention utilizes the combined action of a real-time data acquisition module and a dynamic data analysis module. It acquires current and voltage data during the welding process at a millisecond-level sampling frequency, and employs deep learning algorithms and big data analytics to perform real-time and precise analysis of the acquired current and voltage fluctuation signals. This enables rapid identification of various abnormalities during the welding process, automatic selection and recording of abnormal point coordinates for subsequent in-depth analysis of the causes, suspension of welding operations, and issuance of shutdown warnings. Therefore, it can monitor welding quality in real-time and accurately, promptly detect and address welding abnormalities, prevent defect expansion, ensure the stability and reliability of welding quality, and improve product qualification rates.

[0078] The above specific embodiments should not be construed as limiting the scope of protection of the present invention. For those skilled in the art, any alternative improvements or modifications made to the embodiments of the present invention shall fall within the scope of protection of the present invention.

[0079] Any aspects of this invention not described in detail are well-known to those skilled in the art.

Claims

1. A welding quality monitoring method based on real-time acquisition and dynamic analysis, characterized in that, The monitoring method includes a monitoring system, the monitoring system comprising: The real-time data acquisition module is used to acquire current and voltage data during the welding process in real time at a sampling frequency of milliseconds using a high-speed, high-precision data acquisition card. The data dynamic analysis module is used to perform real-time and accurate analysis of the collected current and voltage fluctuation signals using deep learning algorithms and big data analysis, so as to quickly identify various abnormal information in the welding process. The monitoring method includes the following steps: S1, set the weighting coefficient and influence ratio of DC gas shielded welding; S2, set the weighting coefficient and influence ratio of pulse gas shielded welding; S3, calculate the corresponding reference frequency; S4, calculate the corresponding defect tendency rate; Calculating the corresponding reference frequency involves the following steps: S3.1, the short-circuit transition frequency is calculated using the wire feed speed and arc voltage; the calculation formula is as follows: Short-circuit transition frequency = wire feed speed / (arc length + short-circuit burn-back length) × welding wire diameter; S3.2, Determine the current frequency and voltage frequency based on the pulse transition frequency of the welding robot; S3.3, set current to I s , set voltage to U s , set frequency to P s , set pulse transition frequency to G s , obtain reference frequency F via relationship coefficient r = θ (U S , I s , G S ); Let I be the real-time current of the welding robot at time t during the welding process. a (t), real-time voltage is U a (t), real-time power is P a (t); combined with the calculated current frequency F I (t), voltage frequency F u (t) and power frequency F P The defect tendency rate δ(t) is obtained as follows: ； Where a, b, c, d, e, g are weighting coefficients.

2. The welding quality monitoring method based on real-time acquisition and dynamic analysis according to claim 1, characterized in that, The weighting coefficients for DC gas shielded welding and pulsed gas shielded welding both include current deviation, voltage deviation, power deviation, current frequency deviation, voltage frequency deviation, and power frequency deviation. The current deviation is used to determine the welding wire melting speed and penetration depth; the voltage deviation is used to control the arc length and energy distribution; the power deviation is used to comprehensively reflect the heat input; the current frequency deviation is used to determine the droplet transition frequency and heat input distribution; the voltage frequency deviation is used to affect the arc stability; and the power frequency deviation is used to indirectly affect the periodic fluctuations of the heat input. For the weighting coefficients of DC gas shielded welding, the influence of current deviation is 40%, the influence of voltage deviation is 30%, the influence of power deviation is 15%, the influence of current frequency deviation is 8%, the influence of voltage frequency deviation is 5%, and the influence of power frequency deviation is 2%. For the weighting coefficients of pulsed gas shielded welding, the influence of current deviation is 25%, the influence of voltage deviation is 20%, the influence of power deviation is 15%, the influence of current frequency deviation is 15%, the influence of voltage frequency deviation is 10%, and the influence of power frequency deviation is 15%.

3. The welding quality monitoring method based on real-time acquisition and dynamic analysis according to claim 1, characterized in that: The monitoring system can record various data during the welding process in real time at 100ms intervals, including current, voltage, oscillation frequency, oscillation amplitude, and welding speed. It can obtain the trajectory path information of the welding operation task by interacting with the motion control system of the navigation wheeled mobile platform and the industrial robotic arm. The data is organized according to time sequence and task number and stored in solid-state drive to establish a dual indexing mechanism based on time sequence and task number.

4. The welding quality monitoring method based on real-time acquisition and dynamic analysis according to claim 3, characterized in that: The navigation wheeled mobile platform is equipped with high-precision laser navigation and visual navigation functions, and is equipped with a path planning algorithm. In actual working scenarios, the welding robot first scans the surrounding environment with LiDAR to build a map model, and then combines the image information obtained by the visual sensor to identify obstacles and target positions in the work area in real time. According to the preset task instructions and map information, the path planning algorithm automatically generates the optimal movement path, controls the navigation wheeled mobile platform to move to the designated work position at a stable speed and in a precise direction, and ensures that the robot can operate efficiently and safely in complex working environments.

5. The welding quality monitoring method based on real-time acquisition and dynamic analysis according to claim 3, characterized in that: The load capacity, repeatability, joint angle, movement speed, and acceleration of the industrial robotic arm can all be adjusted to achieve precise motion control.

6. The welding quality monitoring method based on real-time acquisition and dynamic analysis according to claim 1, characterized in that: The monitoring system establishes a stable communication connection with the MES system via Ethernet or a wireless local area network. When the MES system issues a work task scheduling instruction, the system first parses and verifies the received instruction to ensure its accuracy and completeness. Then, according to the instruction content, it controls the navigation wheeled mobile platform to move to the designated workstation, while simultaneously adjusting the industrial robotic arm to a specific posture and parking position. The system receives and parses the robot operation program from the MES system, sends the program parameters to the control systems of the welding system and the industrial robotic arm, and starts and executes the operation program. During the operation, the system provides real-time feedback to the MES system on the robot's working status and task progress, realizing real-time monitoring and management of the production process.

Images