Welding quality monitoring method and system based on signal fusion

Abstract

The present invention provides a welding quality monitoring method and system based on signal fusion, which relates to the technical field of welding quality monitoring. The method comprises: first, obtaining the current welding state based on the arc image captured by the image acquisition device for the welding point; then calculating the electrical signal characteristic value based on the voltage and current data collected by the electrical signal acquisition device for the welding gun; and then using the data analysis device to analyze the corresponding electrical signal characteristic value according to the current welding state to determine the final result of the current welding quality. This method can alleviate the technical problems of low efficiency and low accuracy of the existing production line welding quality monitoring method, and achieve the technical effect of improving the accuracy of welding quality monitoring.

Description

Technical Field

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

[0002] Currently, welding production lines are widely used in the arc welding field. To monitor the quality of welding on these production lines, offline quality inspection methods such as visual inspection and sampling testing are often used. These methods are inefficient and have low accuracy due to their over-reliance on subjective judgment. The lack of standardized evaluation indicators makes it impossible to accurately judge welding quality. In other words, existing methods for monitoring production line welding quality suffer from technical issues such as low efficiency and low accuracy. Summary of the Invention

[0003] The purpose of the present invention is to provide a welding quality monitoring method and system based on signal fusion to alleviate the technical problems of low monitoring efficiency and low accuracy in the prior art.

[0004] In a first aspect, an embodiment of the present invention provides a welding quality monitoring method based on signal fusion, which is applied to a welding quality monitoring system based on signal fusion. The system includes: an image acquisition device, an electrical signal acquisition device, and a data analysis device; the method includes:

[0005] Based on the arc image captured by the image acquisition device for the welding point, the current welding state is obtained; the welding state includes normal and abnormal;

[0006] Calculating electrical signal characteristic values based on the voltage and current data collected by the electrical signal acquisition device for the welding gun;

[0007] The data analysis device is used to analyze the corresponding electrical signal characteristic value according to the current welding state to determine the final result of the current welding quality.

[0008] In some optional implementations, the step of acquiring the current welding state based on the arc image captured by the image acquisition device for the welding point includes:

[0009] Continuously collecting arc images of welding points using the above-mentioned image acquisition device;

[0010] Performing visual preprocessing on the arc image to generate visual signal parameters; the visual signal parameters include: the currently identified welding state and the confidence level of the current state;

[0011] Based on the above visual signal parameters, the visually represented welding index Pv is determined.

[0012] In some optional implementations, the electrical signal characteristic values include: characteristic values of voltage and current data and characteristic values of welding stability;

[0013] The step of calculating the above-mentioned electrical signal characteristic value based on the voltage and current data collected by the above-mentioned electrical signal acquisition device for the welding gun includes:

[0014] The above-mentioned electrical signal acquisition device is used to collect the voltage and current data of the welding gun in real time;

[0015] Calculating characteristic values of the voltage and current data based on the voltage and current data of the welding gun collected in real time;

[0016] Based on the characteristic values of the voltage and current data described above, a characteristic value of welding stability is calculated.

[0017] In some optional implementations, the step of calculating the characteristic value of the voltage and current data based on the voltage and current data of the welding gun collected in real time includes:

[0018] Determining characteristic values of the voltage and current data of the welding gun using the first time period as a time slice; the characteristic values of the voltage and current data include: characteristic values of voltage and current of the welding gun in the first time period;

[0019] The above-mentioned voltage characteristic values include: the maximum voltage value, minimum voltage value and average voltage value of the above-mentioned welding gun in the above-mentioned first time period; the above-mentioned current characteristic values include: the maximum current value, minimum current value and average current value of the above-mentioned welding gun in the above-mentioned first time period.

[0020] In some optional implementations, the step of calculating the characteristic value of welding stability based on the characteristic value of the voltage and current data includes:

[0021] Based on the above voltage characteristic value and current characteristic value, the welding stability characteristic value is calculated; the above welding stability characteristic value includes the dry sticking length and arc length ; The above stem elongation The calculation formula is:

[0022] ;

[0023] The above arc length The calculation formula is:

[0024] Arc length = Maximum voltage - stem elongation .

[0025] In some optional implementations, after the step of calculating the electrical signal characteristic value based on the voltage and current data collected by the electrical signal acquisition device for the welding gun, the method further includes:

[0026] Electrically preprocessing the electrical signal characteristic values to generate electrical signal parameters; the electrical signal parameters include: a current welding state and a current characteristic value offset; wherein the characteristic value offset is used to represent a deviation of the characteristic value of the voltage and current data relative to the welding stability characteristic value;

[0027] Based on the above electrical signal parameters, the electrical characterization welding index Pe is determined.

[0028] In some optional implementations, the step of analyzing the corresponding electrical signal characteristic value according to the current welding state to determine the final result of the current welding quality includes:

[0029] Based on the above-mentioned visually characterized welding indicators and the above-mentioned electrically characterized welding indicators, combined with the dynamic weight coefficient parameters, the final result P of the current welding quality is determined; the calculation formula is:

[0030] ;

[0031] Among them, x is the dynamic weight coefficient parameter.

[0032] In a second aspect, an embodiment of the present invention provides a welding quality monitoring system based on signal fusion, the system comprising: an image acquisition device, an electrical signal acquisition device, and a data analysis device;

[0033] The image acquisition device is used to acquire arc images of welding points to obtain the current welding status; the welding status includes normal and abnormal;

[0034] The electrical signal acquisition device is used to calculate the electrical signal characteristic value based on the voltage and current data collected by the welding gun;

[0035] The data analysis device is used to analyze the corresponding electrical signal characteristic value according to the current welding state to determine the final result of the current welding quality.

[0036] In a third aspect, an embodiment of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the method described in any one of the first aspects are implemented.

[0037] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute any method described in the first aspect above.

[0038] The present invention provides a welding quality monitoring method and system based on signal fusion, which includes: first, obtaining the current welding state based on the arc image captured by the image acquisition device for the welding point; then calculating the electrical signal characteristic value based on the voltage and current data collected by the electrical signal acquisition device for the welding gun; and then using the data analysis device to analyze the corresponding electrical signal characteristic value according to the current welding state to determine the final result of the current welding quality; this method can alleviate the technical problems of low efficiency and low accuracy of the existing production line welding quality monitoring method, and achieve the technical effect of improving the accuracy of welding quality monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 A schematic flow chart of a welding quality monitoring method based on signal fusion provided by an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of the dynamic weight calculation principle of a welding quality monitoring method based on signal fusion provided by an embodiment of the present invention;

[0042] Figure 3 A structural diagram of a welding quality monitoring system based on signal fusion provided by an embodiment of the present invention;

[0043] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0045] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0046] It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures. Some embodiments of the present invention are described in detail below with reference to the accompanying figures. The following embodiments and features of the embodiments may be combined with each other unless there is a conflict.

[0047] Currently, welding production lines are widely used in the arc welding field. To monitor the quality of welding on these lines, offline quality inspection methods such as visual inspection and sampling testing are often used. These methods are inefficient and have low accuracy due to their over-reliance on subjective judgment. The lack of standardized evaluation indicators makes it difficult to accurately judge welding quality.

[0048] In other words, existing methods for monitoring production line welding quality suffer from low efficiency and low accuracy. Therefore, embodiments of the present invention provide a welding quality monitoring method and system based on signal fusion to alleviate the technical problems of low efficiency and low accuracy in existing production line welding quality monitoring methods.

[0049] To facilitate understanding of this embodiment, a welding quality monitoring method based on signal fusion disclosed in an embodiment of the present invention is first described in detail. Figure 1 The figure shows a flow chart of a welding quality monitoring method based on signal fusion. The method is applied to a welding quality monitoring system based on signal fusion. The system includes: an image acquisition device, an electrical signal acquisition device, and a data analysis device. The method can be performed by an electronic device and mainly includes the following steps S110 to S130:

[0050] S110: Based on the arc image captured by the image acquisition device for the welding point, the current welding state is acquired; the welding state includes normal and abnormal;

[0051] S120: Calculating an electrical signal characteristic value based on voltage and current data collected by the electrical signal acquisition device for the welding gun;

[0052] The electrical signal characteristic values include: characteristic values of voltage and current data and characteristic values of welding stability;

[0053] S130: Utilizing a data analysis device to analyze corresponding electrical signal characteristic values according to the current welding state, and determining a final result of the current welding quality.

[0054] In one embodiment, the step of obtaining the current welding state based on the arc image captured by the image acquisition device for the welding point in S110 includes:

[0055] (S111) continuously collecting arc images of welding points using an image acquisition device;

[0056] (S112) performing visual preprocessing on the arc image to generate visual signal parameters; the visual signal parameters include: the currently recognized welding state and the confidence level of the current state;

[0057] As a specific example, the arc image can be input into the neural network algorithm model in real time. The neural network judges that the input is image data and the output is whether the content in the image is the welding state Sv (0, 1) (that is, normal or abnormal), and the corresponding confidence level Psv (0-1).

[0058] ( S113 ) Determine a visually represented welding index Pv based on the visual signal parameters.

[0059] As a specific example, Pv = .

[0060] In one embodiment, the step of calculating the electrical signal characteristic value based on the voltage and current data collected by the electrical signal acquisition device for the welding gun in S120 includes:

[0061] (S121) using an electrical signal acquisition device to collect voltage and current data of the welding gun in real time;

[0062] (S122) calculating characteristic values of the voltage and current data based on the voltage and current data of the welding gun collected in real time;

[0063] ( S123 ) Calculate a welding stability characteristic value based on the characteristic value of the voltage and current data.

[0064] In one embodiment, the step of calculating characteristic values of the voltage and current data based on the voltage and current data of the welding gun collected in real time (S122) includes:

[0065] Taking the first time period as a time slice, characteristic values of the voltage and current data of the welding gun are determined.

[0066] Among them, the characteristic values of voltage and current data include: voltage characteristic values and current characteristic values of the welding gun in the first time period; voltage characteristic values include: maximum voltage value, minimum voltage value and average voltage value of the welding gun in the first time period; current characteristic values include: maximum current value, minimum current value and average current value of the welding gun in the first time period.

[0067] As a specific example, the first time period can be 10ms, that is, within the continuous 10ms time slice collected in real time, the maximum voltage value Vmax, minimum voltage value Vmin and average voltage value Vmean, as well as the maximum current value Imax, minimum current value Imin and average current value Imean of the welding gun are determined.

[0068] In one embodiment, the step of calculating the welding stability characteristic value based on the characteristic value of the voltage and current data (S123) includes:

[0069] Based on the voltage characteristic value and the current characteristic value, a welding stability characteristic value is calculated.

[0070] Among them, the characteristic values of welding stability include dry extension and arc length Stem elongation The calculation formula for Uext is:

[0071] ;

[0072] Right now: ;

[0073] Arc length The calculation formula of Ua is:

[0074] Arc length = maximum voltage value - dry elongation; that is: Ua = Vmax-Uext.

[0075] In one embodiment, after the step of calculating the electrical signal characteristic value based on the voltage and current data collected by the electrical signal acquisition device for the welding gun in S120, the method further includes:

[0076] (S124) Electrically preprocessing the electrical signal characteristic value to generate electrical signal parameters; the electrical signal parameters include: a current welding state and a current characteristic value offset; wherein the characteristic value offset is used to represent a deviation of the characteristic value of the voltage and current data relative to the welding stability characteristic value;

[0077] As a specific example, the calculation of the above eigenvalue offset includes:

[0078] The voltage characteristic values (Vmax, Vmin, Vmean), current characteristic values (Imax, Imin, Imean), and welding stability characteristic values (Uext, Ua) are recorded at a sampling frequency of 10ms since the start of welding, and eight curves are plotted. Kalman filtering is then applied to each curve to calculate its prior estimate.

[0079] Taking the maximum voltage Vmax as an example, we can calculate the a priori estimate Vmax-p. Once the latest Vmax data is obtained, we can calculate the deviation between the measured value and the a priori estimate. The deviation is calculated as ΔVmax = |V_max-V_(max-p) | / V_(max-p).

[0080] At the same time, calculate the deviations of the eight eigenvalues: ΔVmax, ΔImax, ΔVmin, ΔImin, ΔVmean, ΔImean, ΔUext, ΔUa, and then average these eight deviations to obtain the eigenvalue offset;

[0081] That is: Δ = (ΔVmax+ΔImax+ΔVmin+ΔImin+ΔVmean+ΔImean+ΔUext+ΔUa) / 8.

[0082] The obtained characteristic value offset parameter Δ represents the offset of parameters such as voltage and current during the welding process relative to the stable operation value. The larger the offset, the worse the welding quality.

[0083] (S125) Determine an electrically characterized welding index Pe based on the electrical signal parameters.

[0084] As a specific example, the electrical signal parameters (current welding state and current characteristic value offset) are normalized to obtain the electrical characterization welding index Pe= .

[0085] Since when any dimension of the visual signal and the electrical signal detects obvious abnormality, it can be judged that the welding is abnormal at this time, so the dynamic weight method can be used for calculation (see the schematic diagram of the dynamic weight calculation principle for details). Figure 2 In one embodiment, the step of analyzing the corresponding electrical signal characteristic value according to the current welding state in S130 to determine the final result of the current welding quality includes:

[0086] Based on the visually represented welding index Pv and the electrically represented welding index Pe, combined with the dynamic weight coefficient parameter, the final result P of the current welding quality is determined; the calculation formula is:

[0087] ;

[0088] Among them, x is the dynamic weight coefficient parameter.

[0089] The normal and abnormal P value ranges can be flexibly divided according to actual conditions. For example, after testing, they can be preliminarily divided into:

[0090] Welding results: .

[0091] Specifically, the signal fusion-based welding quality monitoring method provided by an embodiment of the present invention fuses signal data and results from two different dimensions collected by two sensors (an image acquisition device and an electrical signal acquisition device) using weights to obtain a weld quality result for the entire welding process. The specific fusion process involves processing the visual image data and electrical signal data collected in the same time slice. The visual signal acquires two important parameters: one represents the currently identified welding state (normal or abnormal), and the other represents the confidence level of the current state, ranging from 0 to 1. The electrical signal also acquires two important parameters: the current welding state and the degree to which the current characteristic value deviates from the normal state. By calculating these four data points according to the weights, the final result of the current welding quality can be determined.

[0092] In addition, the embodiment of the present invention also provides a welding quality monitoring system based on signal fusion, see Figure 3 As shown, the system includes: an image acquisition device 310, an electric signal acquisition device 320 and a data analysis device 330; wherein the image acquisition device is used to acquire the arc image of the welding point to obtain the current welding state; the welding state includes normal and abnormal; the electric signal acquisition device is used to calculate the electric signal characteristic value based on the voltage and current data collected by the welding gun; the data analysis device is used to analyze the corresponding electric signal characteristic value according to the current welding state to determine the final result of the current welding quality.

[0093] As a specific example, the image acquisition device can be a camera installed in the production line area for real-time image data capture of welds. The electrical signal acquisition device is generally connected to the welding gun and is used to collect the welding gun's voltage and current signals in real time. The electrical signal acquisition device can include: a current sensor, an attenuator, and a high-speed data acquisition card. The current sensor is used to convert the welding gun current during welding into a voltage signal that can be collected; the attenuator is used to attenuate the welding gun voltage during welding into a regular voltage signal that can be collected; and the high-speed data acquisition card is used to collect the welding gun's voltage and current signals in real time. The data analysis device can be a high-performance computer, server, or electronic terminal for real-time data processing. The collected data is calculated using a model generated by machine learning to ultimately obtain real-time data on welding quality, which is then displayed, analyzed, and stored.

[0094] Currently, many vision-based welding monitoring systems exist in the field. These use cameras or visual sensors to capture images or videos of the welding process and, through image processing and pattern recognition algorithms, detect welds, defects, and deviations. However, these systems typically rely solely on visual information and are unable to monitor and analyze arc characteristics and welding parameters in real time. Furthermore, some electrical signal-based welding monitoring systems exist in the field. These systems collect signals such as current, voltage, and arc characteristics during the welding process and use signal processing and feature extraction algorithms to analyze weld quality. However, these systems primarily focus on arc characteristics and fail to provide intuitive information about weld shape and defects. Traditional offline production line welding quality monitoring methods (such as visual inspection and spot checks) not only require manual intervention, are inefficient, and prone to subjective judgment, but also fail to provide real-time welding quality monitoring and early warning capabilities.

[0095] Compared to the above-mentioned prior art, the welding quality monitoring method and system based on signal fusion provided by the embodiments of the present invention fuses visual and electrical signals to perform real-time production line welding quality monitoring, which has the following advantages:

[0096] 1. Comprehensiveness: By integrating visual and electrical signals, this method provides more comprehensive welding quality monitoring. It can simultaneously capture key information such as weld shape, defect information, arc characteristics, and welding parameters, enabling a comprehensive assessment of welding quality. Compared to traditional visual or electrical monitoring systems, this method provides a more comprehensive and accurate welding quality assessment.

[0097] 2. Real-time: This method realizes real-time welding quality monitoring, which can detect abnormal conditions in time during the welding process and take measures; compared with offline detection methods, it can quickly feedback welding quality problems and reduce the defect rate of subsequent processes.

[0098] 3. Automation: Using machine learning and deep learning technologies, this method can automatically learn and adapt to different welding quality characteristics; it does not rely on manual judgment, reduces the impact of human factors on monitoring results, and improves the accuracy and consistency of monitoring.

[0099] 4. Efficiency improvement: Through real-time monitoring and early warning functions, this method can improve the efficiency of the welding production line; it can quickly detect welding quality problems and make timely adjustments and corrections, reducing the production of defective products and improving the yield rate of the production line.

[0100] 5. Easy-to-use operation and control: The welding quality monitoring system based on signal fusion provided by the embodiment of the present invention can also perform system integration and interface design, provide a user-friendly operation interface and simple operation method, so that operators can conveniently set parameters, view monitoring results and perform quality control operations on a data analysis device (electronic terminal) with interactive functions, reducing the complexity of manual operation and the risk of misoperation.

[0101] 6. Scalability and Adaptability: The technical solutions provided by the embodiments of this invention are scalable and adaptable, and can be customized and adjusted according to different welding processes and requirements. The fusion of visual and electrical signals can adapt to the characteristics of different welding processes and materials, and can be flexibly applied to different types of welding tasks.

[0102] In summary, compared with the existing visual monitoring systems, electrical monitoring systems and traditional quality inspection methods used separately for welding quality inspection, the real-time production line welding quality monitoring method that integrates visual and electrical signals has many advantages and beneficial effects, such as comprehensive information acquisition, real-time monitoring and early warning functions, automated monitoring and analysis, improved production efficiency and quality control, simple and easy operation and control, as well as scalability and adaptability. It can provide more accurate and reliable welding quality monitoring and control, which is reflected in the improvement of working performance, reduction of production cost and energy loss, increase of stability, and ease of operation and control, which helps to improve the quality and production efficiency of the welding process.

[0103] The signal fusion-based welding quality monitoring system provided in the embodiment of the present application can be specific hardware on the equipment or software or firmware installed on the equipment, etc. The implementation principle and technical effects of the device provided in the embodiment of the present application are the same as those in the aforementioned method embodiment. For the sake of brief description, for parts not mentioned in the device embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here. The signal fusion-based welding quality monitoring system provided in the embodiment of the present application has the same technical features as the signal fusion-based welding quality monitoring method provided in the aforementioned embodiment, so it can also solve the same technical problems and achieve the same technical effects.

[0104] An embodiment of the present application further provides an electronic device. Specifically, the electronic device includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned embodiments.

[0105] Figure 4A structural diagram of an electronic device provided in an embodiment of the present application, the electronic device 400 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0106] Memory 41 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between the system network element and at least one other network element is achieved through at least one communication interface 43 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0107] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0108] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the process definition device disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0109] Processor 40 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method may be completed by hardware integrated logic circuits or software instructions in processor 40. The above processor 40 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention may be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or the like. The storage medium is located in the memory 41 , and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0110] Corresponding to the above method, an embodiment of the present application also provides a computer-readable storage medium, which stores machine-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to execute the steps of the above method.

[0111] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0112] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0113] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0114] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, electronic device, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0115] It should be noted that similar numbers and letters represent similar items in the accompanying drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A welding quality monitoring method based on signal fusion, characterized in that: Applied to a welding quality monitoring system based on signal fusion, the system includes: an image acquisition device, an electrical signal acquisition device and a data analysis device; the method includes: Based on the arc images continuously collected by the image acquisition device for the welding spot, the arc images are visually preprocessed using a neural network algorithm model to generate visual signal parameters; the visual signal parameters include: the currently identified welding state and the confidence level of the current state; based on the visual signal parameters, a visually represented welding index Pv is determined; the welding state includes normal and abnormal; based on the voltage and current data collected in real time by the electrical signal acquisition device for the welding gun, electrical signal characteristic values are calculated; the electrical signal characteristic values include: characteristic eigenvalues of the voltage and current data and welding stability eigenvalues; the welding stability eigenvalues include dry stickout-related eigenvalues and arc length-related eigenvalues; the calculation formula for the dry stickout-related eigenvalues is: ； The calculation formula of the arc length related characteristic value is: arc length related characteristic value = maximum voltage value - stem extension related characteristic value; Electrically preprocessing the electrical signal characteristic values to generate electrical signal parameters; the electrical signal parameters include: a current welding state and a current characteristic value offset; wherein the characteristic value offset is used to represent the characteristic value of the voltage and current data and the offset of the welding stability characteristic value relative to a stable operation value; and determining an electrically characterized welding index Pe based on the electrical signal parameters; The data analysis device is used to dynamically assign weights to the corresponding electrical signal characteristic values according to the current welding state and the confidence level of the current state, and the final result of the current welding quality is determined by a formula; the formula is: ； Among them, x is the dynamic weight coefficient parameter, Pv is the welding index characterized by sensation, and Pe is the welding index characterized by electricity.

2. The welding quality monitoring method based on signal fusion according to claim 1, characterized in that: The step of calculating characteristic values of the voltage and current data based on the voltage and current data of the welding gun collected in real time includes: Determining characteristic values of voltage and current data of the welding gun using a first time period as a time slice; the characteristic values of the voltage and current data include: characteristic values of voltage and current of the welding gun within the first time period; The voltage characteristic values include: the maximum voltage value, minimum voltage value and average voltage value of the welding gun in the first time period; the current characteristic values include: the maximum current value, minimum current value and average current value of the welding gun in the first time period.

3. A welding quality monitoring system based on signal fusion, characterized in that: include: Image acquisition device, electrical signal acquisition device and data analysis device; The image acquisition device is used to: perform visual preprocessing on arc images continuously acquired from welding points using a neural network algorithm model to generate visual signal parameters; The visual signal parameters include: the currently identified welding state and the confidence level of the current state; based on the visual signal parameters, determining the visually represented welding index Pv, wherein the welding state includes normal and abnormal; The electrical signal acquisition device is used to calculate electrical signal characteristic values based on the voltage and current data collected in real time by the welding gun; the electrical signal characteristic values include: characteristic characteristic values of the voltage and current data and welding stability characteristic values; the welding stability characteristic values include dry stickout-related characteristic values and arc length-related characteristic values; the calculation formula of the dry stickout-related characteristic values is: ； The calculation formula of the arc length related characteristic value is: arc length related characteristic value = maximum voltage value - stem extension related characteristic value; The data analysis device is configured to: electrically preprocess the electrical signal characteristic values to generate electrical signal parameters; the electrical signal parameters include: a current welding state and a current characteristic value offset; wherein the characteristic value offset is used to represent the characteristic value of the voltage and current data and the offset of the welding stability characteristic value relative to a stable operation value; and determine an electrically characterized welding index Pe based on the electrical signal parameters; The data analysis device is further configured to dynamically assign weights to the corresponding electrical signal characteristic values according to the current welding state and the confidence level of the current state, and determine the final result of the current welding quality using a formula; the formula is: ； Among them, x is the dynamic weight coefficient parameter, Pv is the welding index characterized by sensation, and Pe is the welding index characterized by electricity.

4. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 2 are implemented.

5. A computer-readable storage medium, characterized in that The computer-readable storage medium stores machine-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method according to any one of claims 1 to 2.

Images