Surfacing process quality monitoring method, system and equipment

Abstract

The invention relates to the technical field of welding quality detection, in particular to a surfacing process quality monitoring method, system and equipment, and the method comprises the steps that a dynamic parameter set of the surfacing process is obtained in real time, and the dynamic parameter set comprises arc characteristic parameters, temperature field distribution parameters and mechanical state parameters; setting an edge computing node, accessing the welding quality prediction model, inputting a dynamic parameter set, and outputting a quality evaluation result containing a defect probability and a fusion depth prediction value; a welding parameter adjusting instruction is generated based on the quality evaluation result, and the operation states of a welding power source and a wire feeding mechanism are adjusted in real time; and updating the dynamic parameter set according to the welding parameter adjusting instruction and transmitting the dynamic parameter set to the industrial control switchboard based on the edge computing node. According to the invention, the problem of uncontrollable instantaneous quality fluctuation caused by strong coupling of multiple physical fields in the surfacing process is effectively solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of welding quality detection, and in particular to a surfacing process quality monitoring method, system and device. BACKGROUND

[0002] Surfacing is an important additive manufacturing technology, widely used in the field of surface strengthening and repair of mechanical parts. The core process essence is to melt the metal welding wire into droplets by arc heat source, and form a metallurgical bonding surfacing layer on the surface of the base material. This process involves strong coupling of multiple physical fields such as arc physics, molten pool fluid dynamics, and solid phase change: the fluctuation of arc energy directly affects the temperature gradient of the molten pool, while the mechanical vibration of the wire feeding mechanism interferes with the stability of the droplet transfer, ultimately resulting in the instantaneous generation of micro defects such as sudden change of penetration, pores and cracks.

[0003] The current mainstream technical solution in the industry has monitoring lag, and the traditional method of relying on post-weld X-ray or ultrasonic detection usually obtains results after a period of time after the process is completed, and cannot intercept defects caused in a short time scale; online monitoring only analyzes parameters such as arc characteristics, temperature field and mechanical state separately, in fact, the fluctuation of wire feeding speed will change the molten pool flow field through droplet impact force, and then affect the contraction effect of arc plasma, this multi-parameter chain reaction has not been modeled. The above defects are collectively directed at uncontrollable quality fluctuations under the coupling of multiple physical fields. This directly leads to the fact that the surfacing qualification rate of core components of high-end equipment cannot be improved for a long time, and the repair cost is high.

[0004] The information disclosed in this BACKGROUND section is only intended to enhance the understanding of the general background of the present disclosure and is not intended to be a recognition or any form of suggestion that this information constitutes prior art. SUMMARY

[0005] The present application provides a surfacing process quality monitoring method, system and device, which can effectively solve the problems in the background art.

[0006] In order to achieve the above purpose, the technical scheme adopted by the present application is:

[0007] A surfacing process quality monitoring method, the method comprising:

[0008] Real-time acquisition of a set of dynamic parameters of the surfacing process, the set of dynamic parameters including arc characteristic parameters, temperature field distribution parameters and mechanical state parameters;

[0009] Setting an edge computing node and inputting the set of dynamic parameters into a welding quality prediction model to output a quality evaluation result including a defect probability and a penetration prediction value;

[0010] Generate welding parameter adjustment instructions based on quality assessment results and adjust the operating status of welding power supply and wire feeding mechanism in real time;

[0011] The dynamic parameter set is updated according to the welding parameter adjustment instructions and transmitted to the industrial control switchboard based on the edge computing node.

[0012] Furthermore, the quality assessment results including defect probability and penetration prediction are output, including:

[0013] Acquiring quality impact characteristics of each parameter in the dynamic parameter set and establishing a real-time interactive impact relationship based on the quality impact characteristics;

[0014] Performing cross-domain temporal correlation analysis on the real-time interactive influence relationship, and dynamically allocating weight coefficients of the influence of each parameter in the dynamic parameter set on the surfacing quality;

[0015] The defect probability and the penetration depth prediction value are generated synchronously based on the distribution result of the weight coefficient.

[0016] Furthermore, when a high-frequency vibration characteristic indicating an abnormality of the wire feeding mechanism is detected in the mechanical state parameter, an equipment fault instruction is generated and the welding process is interrupted.

[0017] Furthermore, edge computing is performed to obtain quality results, including:

[0018] completing spatiotemporal alignment processing of the dynamic parameter set locally at the edge computing node, and establishing a real-time analysis window synchronized with the dynamic evolution of the molten pool;

[0019] Performing dynamic allocation of the weight coefficients based on the real-time analysis window, while caching historical weight allocation sequences of at least three consecutive windows;

[0020] When it is detected that the communication delay of the industrial control computer exceeds a preset threshold, the historical weight distribution sequence is enabled to generate the quality assessment result, and the result is transmitted in parallel to the industrial control computer and the welding power source for adjustment.

[0021] Furthermore, generating the quality assessment result using the historical weight distribution sequence includes:

[0022] Extracting fluctuation characteristics from the historical weight distribution sequence and identifying the weight offset pattern of the arc energy parameter and the mechanical vibration parameter;

[0023] Performing pattern similarity matching between the coupling strength variation trend of the current real-time analysis window and the weight shift rule;

[0024] When the matching degree is lower than the preset tolerance interval, a compensation factor based on the solidification of the molten pool is generated;

[0025] The compensation factor is used to correct the mean value calculation result of the historical weight distribution sequence, and the quality evaluation result is generated.

[0026] Further, a welding parameter adjustment instruction is generated based on the quality evaluation result, including:

[0027] The coupling relationship between the defect probability and the penetration prediction value is analyzed, and an arc energy adjustment instruction is generated when the defect probability exceeds a preset value;

[0028] According to the degree of deviation of the penetration prediction value from the process reference, a wire feeding speed compensation amount is dynamically calculated and a mechanical state correction instruction is generated;

[0029] The arc energy adjustment instruction and the mechanical state correction instruction are fused to generate a cooperative control instruction set that simultaneously acts on the pulse waveform parameters of the welding power supply and the servo motor of the wire feeding mechanism.

[0030] Further, the running state of the welding power supply and the wire feeding mechanism is adjusted in real time, including:

[0031] The cooperative control instruction set is decomposed into a welding power supply execution subset and a wire feeding mechanism execution subset;

[0032] According to the hardware abstraction layer interface, the welding power supply execution subset is generated into a pulse waveform, and the current rise rate and pulse frequency are dynamically adjusted to match the molten pool oscillation suppression demand;

[0033] Based on the torque ring controller of the servo motor driven by the wire feeding mechanism execution subset, the gradient compensation of the wire feeding speed is completed within a preset time window;

[0034] Synchronously collect the molten pool state feedback data after execution to verify the cooperative effectiveness of the arc energy adjustment instruction and the mechanical state correction instruction.

[0035] Further, based on the updated dynamic parameter set transmitted by a plurality of the edge computing nodes, cross-regional welding quality statistical analysis is performed to generate a global quality process optimization strategy and issue it to the corresponding edge computing nodes.

[0036] A surfacing process quality monitoring system, the system comprising:

[0037] A parameter acquisition module acquires a dynamic parameter set of the surfacing process in real time, and the dynamic parameter set includes arc characteristic parameters, temperature field distribution parameters, and mechanical state parameters;

[0038] A quality evaluation module sets an edge computing node and accesses a welding quality prediction model, inputs the dynamic parameter set, and outputs a quality evaluation result including a defect probability and a penetration prediction value;

[0039] The instruction adjustment module generates a welding parameter adjustment instruction based on the quality evaluation result, and adjusts the operation state of the welding power supply and the wire feeding mechanism in real time.

[0040] The correction transmission module updates the dynamic parameter set according to the welding parameter adjustment instruction and transmits to the industrial computer based on the edge computing node.

[0041] A surfacing process quality monitoring device for implementing the surfacing process quality monitoring method.

[0042] The technical scheme of the present application can achieve the following technical effects:

[0043] The problem of uncontrollable transient quality fluctuation caused by strong coupling of multiple physical fields in the surfacing process is effectively solved.

[0044] The above description is only a summary of the technical scheme of the present application, in order to more clearly understand the technical means of the present application, which can be implemented according to the content of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical scheme in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or the prior art description, obviously, the drawings in the following description are only some embodiments described in the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0046] Figure 1 It is a flowchart of a surfacing process quality monitoring method;

[0047] Figure 2 It is a flowchart of obtaining quality evaluation results;

[0048] Figure 3 It is a flowchart of generating welding parameter adjustment instructions;

[0049] Figure 4 It is a structural diagram of a surfacing process quality monitoring system. DETAILED DESCRIPTION

[0050] The technical scheme in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application, obviously, the described embodiments are only some embodiments of the present application, not all the embodiments.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description herein is for describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0052] Embodiment one;

[0053] As Figure 1 shown, the application provides a cladding process quality monitoring method, the method comprising:

[0054] S10: Real-time acquisition of a set of dynamic parameters of the cladding process, the set of dynamic parameters including arc characteristic parameters, temperature field distribution parameters, and mechanical state parameters;

[0055] S20: Setting an edge computing node and accessing a welding quality prediction model, inputting the set of dynamic parameters, and outputting a quality evaluation result including a defect probability and a penetration prediction value;

[0056] S30: Generating a welding parameter adjustment instruction based on the quality evaluation result, and real-time adjusting the operating state of the welding power supply and the wire feeding mechanism;

[0057] S40: Updating the set of dynamic parameters according to the welding parameter adjustment instruction and transmitting to the industrial computer based on the edge computing node.

[0058] Specifically, first, a set of dynamic parameters is acquired in real time during the welding process, the set of dynamic parameters including arc characteristic parameters, temperature field distribution parameters and mechanical state parameters, wherein the arc characteristic parameters can capture voltage and current fluctuations of the arc through an arc sensor, the temperature field distribution parameters are acquired through a thermal imager to obtain changes in the temperature field, and the mechanical state parameters can be acquired through a mechanical sensor to obtain the running state of the welding equipment, these data can be processed through an edge computing node, a welding quality prediction model is used to analyze the data and generate a quality evaluation result, the quality evaluation result is not limited to detecting existing welding defects, but also includes predicting the penetration of the weld, so that early intervention of the welding process is realized; in the preferred embodiment, the edge computing node uses an intelligent prediction model, which can learn and update based on historical data during the welding process, so that the real-time acquired data can be analyzed more accurately, then real-time welding parameter adjustment instructions are generated according to the quality evaluation result, including adjusting the welding current, voltage and adjusting the wire feeding speed, etc., the welding parameter adjustment instructions are directly fed back to the welding power supply and the wire feeding mechanism, so that they can be adaptively adjusted according to the real-time data to ensure the stability and consistency of the welding quality; for example, when it is detected that the welding penetration is lower than the preset standard, the edge computing node can automatically generate instructions to increase the welding current or slow down the wire feeding speed to ensure that the penetration reaches the required standard, at the same time, all parameter updates during the adjustment process are further integrated into the set of dynamic parameters to ensure the real-time and integrity of the data, these optimization steps not only improve the welding quality, but also reduce the operation complexity by reducing human intervention and enhance the adaptive ability; finally, all processed data will be transmitted to the industrial computer through the edge computing node for global data analysis and storage, which provides a basis for subsequent welding process optimization, through such real-time monitoring and adjustment mechanism, the quality control ability of the welding process is improved, and the stability and precision of the entire welding process are improved.

[0059] Through the technical scheme of the present application, the problem of uncontrollable instantaneous quality fluctuation caused by strong coupling of multiple physical fields in the surfacing process is effectively solved.

[0060] Further, as shown in Figure 2 The quality evaluation result includes the defect probability and the penetration prediction value, including:

[0061] Obtain the quality influence characteristics of each parameter in the set of dynamic parameters and establish real-time interactive influence relationship according to the quality influence characteristics;

[0062] Perform cross-domain time sequence correlation analysis on the real-time interactive influence relationship, and dynamically allocate weight coefficients of each parameter in the set of dynamic parameters to the influence on the surfacing quality;

[0063] Synchronously generate the defect probability and the penetration prediction value based on the allocation result of the weight coefficients.

[0064] As a preferred embodiment of the above-mentioned examples, firstly, the real-time acquisition of the dynamic parameter set in practice, high-precision sensor arrays are used to capture accurate data of arc characteristics, including arc length, stability, and current-voltage fluctuation; it is also important to monitor the temperature field distribution through infrared temperature measurement devices to ensure accurate data entry in high-heat areas; mechanical state parameters mainly use vibration monitors and displacement sensors to collect dynamic information of the welding table and mechanism to assist in analyzing the quality of surfacing; secondly, the setting of the edge computing node requires certain computing power, usually embedded systems with high processing power are used to run the welding quality prediction model, these models are based on machine learning algorithms, which analyze the input dynamic parameter set and output quality evaluation results containing defect probability and penetration prediction value, in order to improve the accuracy and real-time of analysis, the model needs to constantly update the training data to cope with changes in different materials and welding environments; based on the quality evaluation results, generate welding parameter adjustment instructions, usually use control logic to adjust the welding power source and wire feeding mechanism in real time, specifically, the welding current, voltage, or wire feeding speed can be adjusted to adapt to the dynamically changing welding environment, this real-time adjustment ensures the stability of the welding quality, thereby achieving effective control of welding defects; finally, update the dynamic parameter set according to the adjustment instruction, while ensuring the real-time and integrity of the data, based on the edge computing node, real-time transmission of the updated dynamic parameter set to the industrial computer, realizing centralized data management and subsequent analysis optimization.

[0065] Further, when high-frequency vibration characteristics representing abnormal wire feeding mechanism are detected in the mechanical state parameters, a device fault instruction is generated and the welding process is interrupted.

[0066] As a preferred embodiment of the above-mentioned embodiment, in order to ensure the stability and normal operation state of the wire feeding mechanism, high-frequency vibration monitoring of the mechanical state of the wire feeding mechanism is performed by means of a vibration sensor. The vibration sensor collects vibration data of the wire feeding mechanism in real time, forming detailed vibration characteristic records. These vibration characteristic information is a fine representation of the state of the machine. When the wire feeding mechanism is in a normal operating state, the vibration characteristics remain within a stable frequency range. However, when there is an abnormally high frequency vibration, it often indicates a mechanical failure of the wire feeding mechanism, such as bearing failure or wear of parts, etc. Therefore, a vibration characteristic recognition algorithm is set. This algorithm can compare real-time vibration data with pre-set normal vibration characteristics in real time. Once high-frequency vibration characteristics outside the normal range are detected, the algorithm will immediately recognize and classify abnormal signals. Subsequently, device failure instructions are quickly generated. These failure instructions can be transmitted to the welding control through the industrial control system to interrupt the current welding process, preventing potential equipment damage or welding quality problems. In the preferred embodiment, in order to ensure timely and accurate abnormal judgment, the vibration recognition algorithm has a self-learning function, which can continuously update and optimize based on historical operation data to improve the accuracy and sensitivity of detection. For example, if high-frequency vibration characteristics in a specific state are detected multiple times but do not cause damage to the equipment, the threshold value of this characteristic value can be adjusted to improve the adaptability and stability of the system. In addition, after triggering the device failure instruction, a fault log is automatically recorded to facilitate subsequent repair and maintenance operations.

[0067] Further, performing edge computing to obtain quality results includes:

[0068] The spatiotemporal alignment processing of the dynamic parameter set is completed locally at the edge computing node, and a real-time analysis window synchronized with the dynamic evolution of the molten pool is established;

[0069] Based on the real-time analysis window, dynamic allocation of weight coefficients is performed, and at least three historical weight allocation sequences of consecutive windows are cached;

[0070] When the communication delay of the industrial computer is detected to exceed a pre-set threshold, the historical weight allocation sequence is used to generate a quality evaluation result, which is transmitted in parallel to the industrial computer and the welding power source for adjustment.

[0071] As a preferred embodiment of the above-mentioned embodiment, firstly, the edge computing node locally performs spatio-temporal alignment processing on the dynamic parameter set, constructs a real-time analysis window synchronized with the dynamic evolution of the molten pool through high-precision timestamps and spatial recognition of sensor data, and ensures the capture and analysis of transient changes in the welding process, thereby providing timely feedback for the current welding state; after the real-time analysis window is established, weight coefficients are assigned to each dynamic parameter, and dynamic allocation of the weight coefficients is performed; this dynamic allocation mechanism can adjust the importance of each parameter according to the real-time data changes in the welding process, thereby ensuring the accuracy of the welding quality evaluation; in order to effectively utilize historical data, the edge node caches at least three historical weight distribution sequences of consecutive windows; this caching mechanism not only improves the robustness of data processing, but also provides an alternative solution in the case of network delay or abnormality; the preferred embodiment includes enabling the pre-cached historical weight distribution sequence to generate a quality evaluation result when the communication delay between the control system and the industrial computer is detected to exceed a preset threshold; this mechanism ensures that the edge computing node can still provide stable quality evaluation results even in the case of poor network conditions; the generated evaluation result is then transmitted to the industrial computer and the welding power source at the same time, thereby achieving immediate adjustment of the welding parameters and executing real-time adjustment instructions to maintain the stability and consistency of the welding process; this implementation improves the accuracy and efficiency of the surfacing process quality monitoring by using the real-time analysis window, dynamic weight distribution and historical caching mechanism, especially in the case of high communication delay, thereby ensuring efficient operation of the welding process under different working conditions.

[0072] Further, generating a quality evaluation result using a historical weight distribution sequence includes:

[0073] Extracting fluctuation features in the historical weight distribution sequence to identify the weight offset rules of the arc energy parameter and the mechanical vibration parameter;

[0074] Matching the coupling strength change trend of the current real-time analysis window with the weight offset rules in terms of pattern similarity;

[0075] When the matching degree is lower than a preset tolerance interval, generating a compensation factor based on the solidification of the molten pool;

[0076] Using the compensation factor to correct the mean calculation result of the historical weight distribution sequence to generate a quality evaluation result.

[0077] As a preferred embodiment of the above, in the historical sequence analysis, the preferred weight offset law between the arc energy and the mechanical vibration parameters is found out by distribution detection and curve fitting on the weight data of different welding stages, which can reveal the internal relationship of parameter changes under certain conditions and guide the subsequent analysis process; Next, the coupling strength change trend of the current real-time analysis window is detected, and the correlation between the quantitative data is matched with the identified weight offset law in terms of pattern similarity, which is to judge whether the current state meets the expected quality standard by comparing the real-time window data with the typical patterns in the historical weights, if the matching degree is lower than the preset tolerance interval, it means that there is a significant deviation between the observed data and the historical preferred results, at this time, the compensation factor based on the molten pool solidification is generated; The generation of the compensation factor takes into account the uncertain factors that may occur in the welding process, such as uneven heat distribution or material property differences, the application of the compensation factor in the compensation effect is specifically manifested as a detailed correction to the mean calculation result of the historical weight distribution sequence, by adjusting the compensation factor, the weight distribution result can be adjusted, so that the final evaluation result is more suitable for the current welding environment and conditions; For example, when the weld quality is lower than expected due to excessive mechanical vibration in a certain welding process, identify this anomaly and adjust the weight sequence through the compensation factor, so that the quality evaluation result can reflect the welding status after compensation, so as to further optimize and adjust the welding parameters.

[0078] Further, as shown in Figure 3 The welding parameter adjustment instruction is generated based on the quality evaluation result, including:

[0079] The coupling relationship between the defect probability and the penetration prediction value is analyzed, and when the defect probability exceeds the preset value, the arc energy adjustment instruction is generated;

[0080] According to the degree of deviation of the penetration prediction value from the process benchmark, the compensation amount of the wire feeding speed is dynamically calculated and the mechanical state correction instruction is generated;

[0081] The arc energy adjustment instruction and the mechanical state correction instruction are fused to generate a cooperative control instruction set that simultaneously acts on the pulse waveform parameters of the welding power supply and the servo motor of the wire feeding mechanism.

[0082] As a preferred embodiment of the above-mentioned embodiment, first, after receiving the quality evaluation result, the coupling relationship between the defect probability and the penetration prediction value is analyzed to determine the adjustment strategy of the welding parameters. When the defect probability exceeds the preset threshold, it means that some unstable factors in the welding process may cause the welding quality to decrease. Therefore, an arc energy adjustment instruction is generated to achieve real-time optimization control of the arc energy. The increase or decrease of the arc energy can directly affect the stability of the welding and thus the welding quality. At the same time, the compensation amount of the wire feeding speed is calculated for the condition that the penetration prediction value deviates from the process reference. This calculation is dynamic and can comprehensively consider the deviation degree of the current welding parameters from the process reference to ensure the effectiveness and adaptability of the compensation amount. Through accurate adjustment of the wire feeding speed, the penetration is improved to the ideal state. The generated mechanical state correction instruction not only adjusts the wire feeding speed but also may involve fine control of the wire feeding tension and angle to achieve the best state matching in the welding process. Further, the arc energy adjustment instruction and the mechanical state correction instruction are fused to generate a set of collaborative control instructions that simultaneously act on the welding power source and the wire feeding mechanism. For the control of the welding power source, the instruction set includes changes in the adjustment of the pulse waveform parameters such as frequency and amplitude. For the wire feeding mechanism, the flexible adjustment of the wire feeding speed is realized through accurate control of the servo motor.

[0083] Further, the operating states of the welding power source and the wire feeding mechanism are adjusted in real time, including:

[0084] The collaborative control instruction set is divided into a welding power source execution subset and a wire feeding mechanism execution subset;

[0085] According to the hardware abstraction layer interface, the welding power source execution subset generates a pulse waveform, dynamically adjusts the current rise rate and pulse frequency to match the molten pool oscillation suppression requirement;

[0086] Based on the torque ring controller of the servo motor driven by the wire feeding mechanism execution subset, the gradient compensation of the wire feeding speed is completed within a preset time window;

[0087] Synchronously collect the molten pool state feedback data after execution to verify the collaborative effectiveness of the arc energy adjustment instruction and the mechanical state correction instruction.

[0088] As a preferred embodiment of the above-mentioned embodiment, first, the cooperative control instruction set is disassembled into two execution subsets: a welding power supply execution subset and a wire feeding mechanism execution subset, which respectively involve specific control parameters for the power supply and wire feeding and perform corresponding operations through the hardware abstraction layer interface. For the welding power supply execution subset, the pulse waveform is generated in detail, and the current rise rate and pulse frequency are dynamically adjusted. The purpose of this is to match the needs of molten pool oscillation suppression and ensure the stability of the molten pool during welding, while improving the welding quality. Precise control of the current and oscillation suppression function make the adjustment of arc energy more effective. Second, for the wire feeding mechanism execution subset, torque ring controllers of the driving servo motor are used for control. The torque ring controller can complete gradient compensation of the wire feeding speed within a preset time window. The flexibility and high-precision control of the servo motor ensure stable speed changes during wire feeding, ensuring synchronization of material supply and arc energy. This design ensures the stability of the wire feeding mechanism under high load, while quickly responding to the changing needs of the welding power supply. In the optimization embodiment, the molten pool state feedback data after execution is collected. Through this feedback mechanism, the cooperative effect of the arc energy adjustment instruction and the mechanical state correction instruction can be verified. The verification process includes detailed comparison of the temperature distribution, cooling rate, and solidification morphology of the molten pool to ensure that the adjusted welding parameters achieve the expected effect. Feedback data is not only used for current process verification, but also serves as a source of data for future optimization and deep learning, providing a reference for subsequent welding processes.

[0089] Further, based on the updated dynamic parameter set transmitted by the multiple edge computing nodes, cross-regional welding quality statistical analysis is performed to generate a global quality process optimization strategy and distribute it to the corresponding edge computing nodes.

[0090] As a preferred embodiment of the above-mentioned embodiment, first, a plurality of edge computing nodes distributed in different regions continuously transmit updated dynamic parameter sets, which contain the welding process live of each region. This real-time transmission ensures the immediacy and comprehensiveness of the data, which can cross different welding environments and process settings to collect diverse data samples. After receiving the dynamic parameter sets from each node, a global welding quality statistical analysis is performed. By combining data mining and machine learning techniques, common characteristics and differences between different nodes are identified, and the welding quality of each region is evaluated. In particular, the statistical analysis covers the comprehensive performance of key parameters such as arc characteristics, temperature field distribution, and mechanical state, providing quantitative basis for further optimization. By comparing and integrating the parameter data transmitted from different regions, the global quality trend is obtained. By evaluating these trend changes and abnormal points, a global quality process optimization strategy is generated, including adjusting welding current, voltage, and wire feed speed to adapt to different welding challenges and improve overall quality. Then, the generated global quality process optimization strategy is distributed to the corresponding edge computing nodes. Each node executes the adapted optimization strategy according to the specific circumstances of its corresponding region to improve the welding effect in real time. For example, for regions with slight differences in steel thickness, the strategy may focus on subtle adjustments to the current, while for regions heavily affected by mechanical vibration, the focus is on stabilizing the operation of the wire feeding mechanism.

[0091] Embodiment two;

[0092] Based on the same inventive concept as the welding process quality monitoring method in the preceding embodiment, the present application also provides a welding process quality monitoring system. As shown in Figure 4 The system includes:

[0093] A parameter acquisition module that acquires a dynamic parameter set of the welding process in real time. The dynamic parameter set includes arc characteristic parameters, temperature field distribution parameters, and mechanical state parameters.

[0094] A quality evaluation module that sets up edge computing nodes and accesses a welding quality prediction model, inputs the dynamic parameter set, and outputs quality evaluation results including defect probability and penetration prediction values.

[0095] An instruction adjustment module that generates welding parameter adjustment instructions based on the quality evaluation results, and adjusts the operating state of the welding power supply and the wire feeding mechanism in real time.

[0096] A correction transmission module that updates the dynamic parameter set according to the welding parameter adjustment instructions and transmits it to the industrial computer based on the edge computing nodes.

[0097] The above-mentioned adjustment system in the present application can be effectively implemented, and the technical effects are as described in the above-mentioned embodiment, which will not be repeated here.

[0098] Embodiment three;

[0099] Based on the same inventive concept as the above-mentioned welding process quality monitoring method, the present application also provides a welding process quality monitoring device for implementing a welding process quality monitoring method.

[0100] The above-mentioned device in the present application can effectively implement a welding process quality monitoring method, and can achieve the technical effects as described in the above-mentioned embodiments, which will not be described here again.

[0101] Although the present application has been described in connection with specific features and embodiments thereof, it is obvious that it can be varied in a variety of ways without departing from the spirit and scope of the application. Accordingly, the description and drawings are to be regarded simply as illustrative in nature and are to be construed only as limiting the scope of the application insofar as it is covered by the following claims. Obviously, various modifications and changes can be made to the present application by those skilled in the art without departing from the scope of the present application. Thus, it is intended that the present application encompass all such modifications and changes and that the application be limited only by the scope of the following claims.

Claims

1. A method for monitoring quality of a surfacing welding process, characterized in that: The method comprises: Real-time acquisition of a dynamic parameter set of the surfacing process, wherein the dynamic parameter set includes arc characteristic parameters, temperature field distribution parameters, and mechanical state parameters; Setting up an edge computing node and connecting it to a welding quality prediction model, inputting the dynamic parameter set, and outputting a quality assessment result including defect probability and penetration prediction value; Generating welding parameter adjustment instructions based on the quality assessment results to adjust the operating status of the welding power supply and wire feeding mechanism in real time; The dynamic parameter set is updated according to the welding parameter adjustment instruction and transmitted to the industrial control switchboard based on the edge computing node.

2. The method for monitoring quality of surfacing process according to claim 1, characterized in that: Output quality assessment results including defect probability and penetration prediction values, including: Acquiring quality impact characteristics of each parameter in the dynamic parameter set and establishing a real-time interactive impact relationship based on the quality impact characteristics; Performing cross-domain temporal correlation analysis on the real-time interactive influence relationship, and dynamically allocating weight coefficients of the influence of each parameter in the dynamic parameter set on the surfacing quality; The defect probability and the penetration depth prediction value are generated synchronously based on the distribution result of the weight coefficient.

3. The method for monitoring quality of surfacing welding process according to claim 2, characterized in that: When a high-frequency vibration feature indicating abnormality of the wire feeding mechanism is detected in the mechanical state parameters, an equipment fault instruction is generated and the welding process is interrupted.

4. The method for monitoring quality of surfacing process according to claim 2, characterized in that: Perform edge computing to achieve quality results, including: completing spatiotemporal alignment processing of the dynamic parameter set locally at the edge computing node, and establishing a real-time analysis window synchronized with the dynamic evolution of the molten pool; Performing dynamic allocation of the weight coefficients based on the real-time analysis window, while caching historical weight allocation sequences of at least three consecutive windows; When it is detected that the communication delay of the industrial control computer exceeds a preset threshold, the historical weight distribution sequence is enabled to generate the quality assessment result, and the result is transmitted in parallel to the industrial control computer and the welding power source for adjustment.

5. The method for monitoring quality of surfacing process according to claim 4, characterized in that: Generating the quality assessment result using the historical weight allocation sequence includes: Extracting fluctuation characteristics from the historical weight distribution sequence and identifying the weight offset pattern of the arc energy parameter and the mechanical vibration parameter; Performing pattern similarity matching between the coupling strength variation trend of the current real-time analysis window and the weight shift rule; When the matching degree is lower than the preset tolerance interval, a compensation factor based on the solidification of the molten pool is generated; The compensation factor is used to correct the mean calculation result of the historical weight distribution sequence to generate the quality assessment result.

6. The method for monitoring quality of surfacing process according to claim 1, characterized in that: Generating a welding parameter adjustment instruction based on the quality assessment result includes: Analyzing the coupling relationship between the defect probability and the predicted penetration value, and generating an arc energy adjustment instruction when the defect probability exceeds a preset value; According to the degree to which the predicted penetration value deviates from the process benchmark, a wire feeding speed compensation amount is dynamically calculated and a mechanical state correction instruction is generated; The arc energy adjustment instruction and the mechanical state correction instruction are integrated to generate a collaborative control instruction set that acts on the pulse waveform parameters of the welding power supply and the servo motor of the wire feeding mechanism at the same time.

7. The method for monitoring quality of surfacing process according to claim 6, characterized in that: Real-time adjustment of the operating status of the welding power source and wire feed mechanism, including: Decomposing the collaborative control instruction set into a welding power source execution subset and a wire feeding mechanism execution subset; generating a pulse waveform from the welding power supply execution subset according to the hardware abstraction layer interface, and dynamically adjusting the current rise rate and pulse frequency to match the oscillation suppression requirements of the weld pool; A torque loop controller for driving a servo motor based on the wire feeding mechanism execution subset completes gradient compensation of the wire feeding speed within a preset time window; Synchronously collect the feedback data of the molten pool state after execution to verify the coordinated effectiveness of the arc energy adjustment instruction and the mechanical state correction instruction.

8. The method for monitoring quality of surfacing process according to claim 1, characterized in that: Based on the updated dynamic parameter set transmitted by multiple edge computing nodes, cross-region welding quality statistical analysis is performed to generate a global quality process optimization strategy and send it to the corresponding edge computing node.

9. A surfacing process quality monitoring system, characterized in that: The system comprises: Parameter acquisition module, which acquires the dynamic parameter set of the cladding process in real time. The dynamic parameter set includes arc characteristic parameters, temperature field distribution parameters and mechanical state parameters; The quality assessment module sets up edge computing nodes and connects to the welding quality prediction model. It inputs a dynamic parameter set and outputs quality assessment results including defect probability and penetration prediction values. The instruction adjustment module generates welding parameter adjustment instructions based on the quality assessment results and adjusts the operating status of the welding power supply and wire feeding mechanism in real time; The modified transmission module updates the dynamic parameter set according to the welding parameter adjustment instructions and transmits it to the industrial control switchboard based on the edge computing node.

10. A cladding process quality monitoring device, used to implement a cladding process quality monitoring method according to claims 1-8.

Images