Low-pressure outer cylinder welding quality monitoring method, system, equipment and medium

Abstract

The invention discloses a low-pressure outer cylinder welding quality monitoring method, system and equipment and a medium, and relates to the technical field of welding quality detection. The invention provides a low-pressure outer cylinder welding quality monitoring method. The low-pressure outer cylinder welding quality monitoring method comprises the steps that welding characteristic parameters of a first welding section in a preset time period are obtained; according to the welding characteristic parameters, a first welding quality score of the first welding section is evaluated based on a welding quality evaluation model, and whether the first welding quality score is larger than a first preset threshold value or not is judged; if not, the welding task is paused, and an alarm signal is sent out; if yes, a second welding quality score of at least one second welding section in the preset time period is obtained; according to all the second welding quality scores and the first welding quality score, pre-estimating a pre-estimated quality score of an unwelded third welding section of the low-pressure outer cylinder, and judging whether the pre-estimated quality score is greater than a second preset threshold value or not; and if the estimated quality score is smaller than or equal to a second preset threshold value, the welding strategy is adjusted.

Description

Technical Field

[0001] The present application relates to the technical field of welding quality detection, and in particular to a method, system, equipment and medium for monitoring the welding quality of a low-pressure outer cylinder. Background Art

[0002] In the manufacturing process of low-pressure outer cylinder, welding is a crucial link, and its welding quality is directly related to the overall performance, reliability and service life of the low-pressure outer cylinder. Low-pressure outer cylinder is usually a key component of large industrial equipment (such as steam turbines, generators, etc.), and is subjected to complex mechanical and thermal stresses. Once there is a problem with the welding quality, it may cause equipment failure, shutdown, and even safety accidents, resulting in huge economic losses and casualties.

[0003] In the prior art, the visual inspection of welding mainly relies on the inspector's naked eye to observe the surface morphology of the weld to determine whether there are obvious defects such as cracks, pores, slag inclusions, etc. This is carried out after the welding is completed and is a post-test. It is unable to monitor the quality changes during the welding process in real time, and cannot promptly discover and correct problems that occur during the welding process, resulting in the possibility that welding defects have already expanded or caused other problems. Summary of the invention

[0004] The main purpose of this application is to provide a low-pressure outer cylinder welding quality monitoring method, system, equipment and medium, aiming to solve the technical problem that the welding quality inspection performed after the low-pressure outer cylinder welding is completed in the prior art is a post-inspection and cannot monitor the quality changes during the welding process in real time.

[0005] To achieve the above objectives, in a first aspect, the present application provides a low-pressure outer cylinder welding quality monitoring method, comprising: Acquire welding characteristic parameters of the first welding section within a preset time period, wherein the welding characteristic parameters include at least one of weld image information, arc sound signal, welding wire consumption information, and welding equipment stability coefficient; According to the welding characteristic parameters, a first welding quality score of the first welding segment is evaluated based on a welding quality evaluation model to determine whether the first welding quality score is greater than a first preset threshold; If not, the welding task is suspended and an alarm signal is issued; If yes, obtaining a second welding quality score of at least one second welding segment within a preset time period; According to all the second welding quality scores and the first welding quality scores, an estimated quality score of the unwelded third welding section of the low-pressure outer cylinder is estimated, and it is determined whether the estimated quality score is greater than a second preset threshold; If the estimated quality score is less than or equal to a second preset threshold, the welding strategy is adjusted.

[0006] Optionally, the step of evaluating the first welding quality score of the first welding segment based on the welding quality evaluation model according to the welding feature parameters and determining whether the first welding quality score is greater than a first preset threshold includes: The expression of the welding quality evaluation model is:

[0007] wherein, represents the first welding quality score, represents the image feature item, represents the weight coefficient of the image feature item, represents the acoustic feature item, represents the weight coefficient of the acoustic feature item, represents the wire consumption item, represents the weight coefficient of the wire consumption item, represents the health compensation gain coefficient, represents the current stability coefficient of the welding equipment, represents the mean value of the historical stability coefficients of the welding equipment, represents the standard deviation of the historical stability coefficients of the welding equipment.

[0008] Optionally, the expression of the image feature item is:

[0009] wherein, represents the weld area, represents the gray value at the (x, y) position of the weld area at time t, represents a Gaussian kernel with a standard deviation of , represents the weld area, represents the two-dimensional convolution operation symbol, represents the ReLU function.

[0010] Optionally, the expression of the acoustic feature item is:

[0011] wherein B represents the band width normalization factor, and represent the characteristic frequency range, represents the arc sound time-domain signal, represents the short-time Fourier transform operator, represents the short-time Fourier transform; represents the complex value at frequency f in the spectrum corresponding to time point t; represents the imaginary unit, represents the acoustic wave propagation time delay compensation, for correcting the acoustic wave propagation time delay The resulting phase shift, represents the frequency variable.

[0012] Optionally, the expression for the wire consumption term is:

[0013] wherein, represents the monitoring time window length, represents the attenuation constant, represents at time the total wire consumption, represents at time the instantaneous consumption rate, represents the current time point, represents the time integration variable.

[0014] Optionally, the step of predicting the predicted quality score of the third weld segment of the low-pressure outer cylinder that has not been welded according to all the second welding quality scores and the first welding quality score, and determining whether the predicted quality score is greater than the second preset threshold includes: The expression for the predicted quality score of the third weld segment is:

[0015] wherein, m represents the number of welded weld segments, k represents the index of the historical weld segment, represents the temporary index variable of the normalization denominator, represents the attenuation coefficient, represents the heat affected zone gradient, represents the heat affected zone gradient coefficient, represents the process parameter correction factor.

[0016] Optionally, the step of adjusting the welding strategy if the predicted quality score is less than or equal to the second preset threshold includes: Perform at least any one of the following operations: According to the key parameter deviation that causes the insufficient predicted quality score, correct the welding process parameters in real time; Weaken the decrease in welding quality caused by equipment failure or component aging; Reduce welding defects caused by spatial position through path planning or operation correction; Force the welding task to pause and start the manual intervention process.

[0017] In a second aspect, the present application provides a low-pressure outer cylinder welding quality monitoring system, including: A feature parameter acquisition module, which is configured to acquire welding feature parameters of a first weld segment within a preset time period, where the welding feature parameters include at least one of weld seam image information, arc sound signal, wire consumption information, and welding equipment stability coefficient; A first welding quality score acquisition module, which is configured to evaluate a first welding quality score of the first weld segment based on the welding feature parameters according to a welding quality evaluation model, and determine whether the first welding quality score is greater than a first preset threshold; If not, suspend the welding task and issue an alarm signal; If so, acquire second welding quality scores of at least one second weld segment within the preset time period; An estimated quality score acquisition module, which is configured to estimate an estimated quality score of a third weld segment of the low-pressure outer cylinder that has not been welded based on all the second welding quality scores and the first welding quality score, and determine whether the estimated quality score is greater than a second preset threshold; A welding strategy adjustment module, which is configured to adjust the welding strategy if the estimated quality score is less than or equal to the second preset threshold.

[0018] In a third aspect, the present application provides a computer device, including a memory and a processor, where a computer program that can run on the processor is stored on the memory, and when the processor executes the computer program, the above-mentioned low-pressure outer cylinder welding quality monitoring method is implemented.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, characterized in that it stores a computer program that can be loaded and executed by a processor to implement the above-mentioned low-pressure outer cylinder welding quality monitoring method.

[0020] Beneficial effects that the present application can achieve: A low-pressure outer cylinder welding quality monitoring method, system, device and medium provided by an embodiment of the present application has at least the following beneficial effects: By acquiring welding feature parameters of a first weld segment within a preset time period and evaluating a first welding quality score according to a welding quality evaluation model, the welding quality can be quantitatively evaluated in real time. When the first welding quality score is not greater than the first preset threshold, the welding task is suspended in time and an alarm signal is issued, which can prevent unqualified welding from continuing; Monitoring the welding process from multiple dimensions can more comprehensively and accurately reflect the welding quality status, and greatly improve the accuracy and reliability of welding quality evaluation compared with single-parameter monitoring; According to the comparison result of the estimated quality score and the second preset threshold, the welding strategy is adjusted in time. This way of dynamically adjusting the welding strategy can prevent the occurrence of welding quality problems in advance, improve the stability of the subsequent welding process and the consistency of welding quality, and improve the overall welding quality. Description of the Drawings

[0021] Figure 1 Schematic flow diagram of the welding quality monitoring method according to an embodiment of the present application; Figure 2 Schematic diagram of the upper half structure of the low-pressure outer cylinder; Figure 3 Schematic diagram of the lower half structure of the low-pressure outer cylinder.

[0022] The realization, functional features and advantages of the purpose of the present application will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0023] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0024] It should be noted that all the directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative position relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0025] In the present invention, unless otherwise clearly defined and limited, the terms "connection", "fixation" and the like should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal connection of two components or the interaction relationship between two components, unless otherwise clearly limited. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0026] In addition, if the descriptions such as "first" and "second" are involved in the embodiments of the present invention, these descriptions of "first", "second", etc. are for descriptive purposes only, and should not be construed as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the meaning of "and / or" appearing throughout the text includes three parallel scenarios. Taking "A and / or B" as an example, it includes scenario A, or scenario B, or the scenario where both A and B are satisfied simultaneously. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0027] Embodiment 1 Refer to Figure 1 , the first embodiment of the present application provides a method for monitoring the welding quality of a low-pressure outer cylinder, including the following operating steps: S10. Obtain the welding characteristic parameters of the first welding section within a preset time period, where the welding characteristic parameters include at least one of weld seam image information, arc sound signal, wire consumption information, and welding equipment stability coefficient.

[0028] Optionally, as Figure 2 and Figure 3 shown, it is a schematic diagram of the upper and lower parts of the overall structure of a nuclear power low-pressure outer cylinder, which is provided with a support structure to facilitate welding of each part of the housing. The main body is made of welded steel plates and reinforced with stiffeners. The outer cylinder structure is a hollow housing. Disassemble and trial-assemble its outer housing through 3D software UG or SolidWorks to ensure that the welding stress distribution is uniform during the welding process, that is, ensure a symmetric structure.

[0029] According to the welding process requirements and actual production experience, determine a suitable time period, such as 5 minutes or 10 minutes, which should be able to fully reflect the stability of the current welding state. Use a high-resolution industrial camera to collect weld image information. The industrial camera is installed at a suitable position and angle to ensure that the weld image of the first weld segment can be clearly captured. Set the shooting parameters of the camera, such as exposure time, focal length, frame rate, etc., to ensure image quality. Continuously collect weld images at a set frequency (such as 10 frames per second) within the preset time period. Use a high-sensitivity sound sensor to collect arc sound signals. The sound sensor is installed close to the welding arc to accurately obtain arc sound signals. Calibrate the sound sensor to ensure that it can accurately capture the frequency and intensity changes of the arc sound. Record the arc sound signals in real time within the preset time period and convert them into digital signals for storage. Install a flow sensor or counting device in the wire feeding system to measure the consumption of the welding wire within the preset time period. Regularly read the data of the sensor and record the consumed length or weight of the welding wire. Obtain various operating parameters of the equipment, such as welding current, voltage, wire feeding speed, gas flow, etc., through the control system or sensors of the welding equipment. Analyze whether these parameters are within the normal range and the operating stability of the equipment, comprehensively evaluate the health status of the welding equipment, and quantify it as a stability coefficient.

[0030] S20. Based on the welding characteristic parameters, evaluate the first welding quality score of the first weld segment according to the welding quality evaluation model, and determine whether the first welding quality score is greater than the first preset threshold.

[0031] Optionally, input characteristic parameters such as the weld image information, arc sound signal, welding wire consumption information, and welding equipment stability coefficient of the first weld segment collected into the welding quality evaluation model. The model calculates based on the input characteristic parameters and outputs the first welding quality score of the first weld segment. This score usually uses a hundred-point system or a ten-point system. Set the first preset threshold according to the welding quality standard and actual production requirements, such as 80 points (hundred-point system). Compare the first welding quality score with the first preset threshold to determine whether it is greater than the first preset threshold.

[0032] S30. If the first welding quality score is less than or equal to the first preset threshold, pause the welding task and send an alarm signal.

[0033] Optionally, through the control system of the welding equipment, send a pause command to immediately stop the welding operation, including stopping wire feeding, cutting off the welding current, etc. Activate the on-site sound and light alarm devices, such as alarm bells, flashlights, etc., to remind the operator to pay attention. At the same time, send the alarm information to relevant monitoring terminals, such as the mobile phone or computer of the workshop director, so as to take measures in a timely manner.

[0034] S40. If the first welding quality score is greater than the first preset threshold, obtain the second welding quality scores of at least one second weld segment within a preset time period.

[0035] Optionally, after the first weld segment, determine at least one second weld segment according to the welding sequence. The welding time of the second weld segment is earlier than that of the first weld segment. For each second weld segment, repeat the operations of S10 and S20 to obtain its welding characteristic parameters, and evaluate the second welding quality score based on the welding quality evaluation model.

[0036] S50. Estimate the estimated quality score of the third weld segment that has not been welded on the low-pressure outer cylinder according to all the second welding quality scores and the first welding quality score, and determine whether the estimated quality score is greater than the second preset threshold.

[0037] Optionally, integrate the first welding quality score and all the second welding quality scores, and analyze the change trend of the welding quality. Methods such as time series analysis and regression analysis can be used to establish an estimation model, and based on the existing welding quality score data, estimate the estimated quality score of the third weld segment. Set the second preset threshold according to the welding quality requirements and the needs of subsequent processing techniques, for example, 75 points (on a 100-point scale). Compare the estimated quality score with the second preset threshold to determine whether it is greater than the second preset threshold.

[0038] S60. If the estimated quality score is less than or equal to the second preset threshold, adjust the welding strategy.

[0039] Optionally, analyze the reasons for the relatively low estimated quality score. Possible reasons include inappropriate welding parameters, problems with the quality of welding materials, and deterioration of equipment performance. According to the analysis results, formulate a corresponding welding strategy adjustment plan, such as adjusting parameters such as welding current, voltage, and welding speed, replacing welding materials, and maintaining and servicing the equipment. Adjust the welding process according to the adjustment plan and re-monitor the welding quality to ensure that the welding quality is effectively improved.

[0040] Optionally, if the estimated quality score is greater than the second preset threshold, it indicates that the expected quality of the unwelded weld segment meets the requirements, do not change the welding strategy, and continue welding according to the original welding strategy.

[0041] Embodiment 2 Based on Embodiment 1, this embodiment provides a method for monitoring the welding quality of a low-pressure outer cylinder, including the following operating steps: S10. Obtain the welding characteristic parameters of the first weld segment within a preset time period, where the welding characteristic parameters include at least one of weld seam image information, arc sound signal, wire consumption information, and welding equipment stability coefficient.

[0042] S20. Based on the welding characteristic parameters, evaluate the first welding quality score of the first welding section according to the welding quality evaluation model, and determine whether the first welding quality score is greater than the first preset threshold.

[0043] Optionally, the step of evaluating the first welding quality score of the first welding section according to the welding characteristic parameters based on the welding quality evaluation model and determining whether the first welding quality score is greater than the first preset threshold includes: The expression of the welding quality evaluation model is:

[0044] In the formula, represents the first welding quality score, represents the image feature item, represents the weight coefficient of the image feature item, represents the acoustic feature item, represents the weight coefficient of the acoustic feature item, represents the wire consumption item, represents the weight coefficient of the wire consumption item, represents the health compensation gain coefficient, represents the current stability coefficient of the welding equipment, represents the mean value of the historical stability coefficients of the welding equipment, represents the standard deviation of the historical stability coefficients of the welding equipment.

[0045] represents the image feature item, which is used to quantify the quality of the weld surface morphology (defects such as pores and undercut).

[0046] represents the acoustic feature item, which is used to capture the arc stability and abnormal discharge characteristics (such as spatter and short circuit).

[0047] represents the wire consumption item, which is used to evaluate the wire supply stability and deposition efficiency.

[0048] Weight constraint conditions , .

[0049] represents the health compensation gain coefficient, which is used to adjust the influence degree of the health compensation item on the overall score.

[0050] represents the current stability coefficient of the welding equipment, which comprehensively reflects the operating state of the welding equipment at time t, including various performance indicators and fault conditions of the equipment. For example, parameters such as the temperature, pressure, and vibration of the equipment can all be components of the stability coefficient.

[0051] represents the mean of the historical stability coefficient of the welding equipment, which represents the average operating state of the welding equipment over a past period. By comparing with the current stability coefficient , the deviation between the current state of the equipment and the historical average state can be understood.

[0052] represents the standard deviation of the historical stability coefficient of the welding equipment, which reflects the degree of fluctuation of the historical operating state of the welding equipment. The larger the standard deviation, the greater the fluctuation of the equipment operating state; the smaller the standard deviation, the more stable the equipment operating state.

[0053] represents the hyperbolic tangent function, which maps the value to the interval. When is close to , tends to 0; when deviates from by a large amount, is close to .

[0054] Optionally, the expression of the image feature item is:

[0055] In the formula, represents the area of the weld region, represents the gray value at time t at the weld region (x, y), represents a Gaussian kernel with a standard deviation of , represents the weld region, represents the two-dimensional convolution operation symbol, represents the Laplace operator, represents the ReLU function.

[0056] represents the area of the weld region, which is used to normalize the integral result so that the value of the image feature item is not affected by the size of the weld region.

[0057] reflects the brightness information of the weld image at different positions and time points.

[0058] is used to smooth the image and reduce noise interference.

[0059] represents the weld region, that is, the integration range is the entire weld region.

[0060] Denotes the two-dimensional convolution operation symbol, which convolves with the image through a Gaussian kernel to extract local features of the image.

[0061] Denotes Gaussian kernel convolution ( pixels), which plays a role in suppressing image noise and retaining the macroscopic morphological features of the weld area.

[0062] Denotes the Laplace operator, which is used to detect edge and texture information in the image and enhance the edge and curvature mutation regions (corresponding to defects such as pores and cracks) Denotes the ReLU function (Rectified Linear Unit), that is , sets negative values in the convolution result to 0, retains the positive value part, and highlights the significant features in the image. Filters negative responses and only retains the features of convex defects (such as weld beads).

[0063] The image feature term reflects the appearance quality of the weld by extracting detailed information such as edges and textures of the weld image, such as the formation of the weld, and the presence of defects such as cracks and pores, and plays an important role in welding quality assessment. The weight coefficient Determines the relative importance of the image feature term in the overall evaluation.

[0064] Optionally, the expression of the acoustic feature term is:

[0065] In the formula, B represents the band width normalization factor, and represent the characteristic frequency range, represents the time-domain signal of the arc sound, represents the short-time Fourier transform operator, represents the short-time Fourier transform; represents the complex value at frequency f in the spectrum corresponding to time point t; represents the imaginary unit, represents the acoustic wave propagation time delay compensation, used to correct the phase shift caused by the acoustic wave propagation time delay, represents the frequency variable.

[0066] B represents the band width normalization factor, which is used to normalize the integration result so that the value of the acoustic feature term is not affected by the band width.

[0067] and represent the characteristic frequency range, which determines the frequency interval of the arc sound signal to be analyzed.

[0068] represents the time-domain signal of the arc sound, which contains the sound information generated during the arc combustion process.

[0069] represents the short-time Fourier transform operator, which transforms the time-domain signal to the frequency domain and obtains the signal amplitude and phase information at different frequencies.

[0070] represents the short-time Fourier transform (window length 32 ms, overlap 50%), which is used to extract the time-frequency characteristics of the arc sound.

[0071] represents the complex value at frequency f in the spectrum corresponding to time point t. For example: if the arc sound signal is framed near time t and the STFT is calculated, then is the spectrum amplitude and phase of this frame signal at frequency f.

[0072] represents the imaginary unit, which is used to represent phase information in complex number operations.

[0073] represents the acoustic wave propagation time delay compensation, which is used to correct the time delay difference caused by different acoustic wave propagation distances. , where c represents the speed of sound and d is the distance.

[0074] represents the phase compensation term, which eliminates the acoustic wave propagation time delay caused by the sensor position.

[0075] represents the frequency variable, which represents a specific frequency point in the frequency domain analysis.

[0076] represents the characteristic frequency band integration, which is used to focus on the high-frequency components related to welding abnormalities (such as spatter, arc instability).

[0077] is used to calculate the amplitude spectrum of the frequency-domain signal after time delay compensation.

[0078] The acoustic feature term reflects the stability and combustion state of the arc by analyzing the frequency characteristics of the arc sound. The frequency and amplitude changes of the arc sound are closely related to parameters such as the arc length, arc voltage, and welding current during the welding process, and can indirectly reflect the welding quality. The weight coefficient determines the relative importance of the acoustic feature term in the overall evaluation.

[0079] Optionally, the expression of the wire consumption term is:

[0080] In the formula, represents the length of the monitoring time window, represents the decay constant, represents at time the total wire consumption, represents at time the instantaneous consumption rate, represents the current time point, represents the time integration variable.

[0081] represents the total wire consumption within the time window .

[0082] The length of the monitoring time window determines the time range for calculating wire consumption.

[0083] The decay constant is used to weight the wire consumption rates at different times, making the consumption rate in the recent period have a greater impact on .

[0084] represents at time the total wire consumption, reflecting the cumulative wire consumption over time.

[0085] represents at time the instantaneous consumption rate, that is, the wire consumption per unit time, reflecting the real-time stability of the deposition process.

[0086] is a decay factor, which decreases as increases, making the contribution of the wire consumption rate farther from the current time to smaller.

[0087] represents the time window integration, evaluating the short-term cumulative effect of wire consumption.

[0088] represents the time integration variable. During the integration process, varies from to and is used to calculate the total wire consumption within this time period.

[0089] represents the current time point, which is the upper limit of integration. Together with the lower limit of integration , it defines the monitoring time window.

[0090] The wire consumption item monitors the wire consumption situation within the monitored time window, reflecting the stability and welding efficiency of the welding process. The change in the wire consumption rate may be related to factors such as welding parameters and welding processes. Abnormal wire consumption may indicate the existence of welding quality problems. The weight coefficient determines the relative importance of the wire consumption item in the overall evaluation.

[0091] For easy understanding, an example is given as follows: It is now necessary to evaluate the welding quality during the circumferential welding of the low-pressure outer cylinder of a steam turbine.

[0092] Assume the initial parameter settings are as follows: Welding position: flat welding; Weight distribution: , , = 0.3; Health compensation gain: ; Equipment stability coefficient: , , ; Monitored time window: , ; Acoustic feature frequency band: , , ; Image processing parameters: Pixels, weld area .

[0093] The calculation process is as follows: Assume that after image processing of the weld at a certain moment: the distribution of the Laplacian-Gaussian convolution result is: the proportion of the positive response area is 15% (porosity, undercut defects); the average positive response intensity is .

[0094] .

[0095] The result of arc sound analysis: the integral value of the energy in the characteristic frequency band is (unit: Pa²·s / Hz); the effective energy after phase compensation is .

[0096] .

[0097] Normalization processing (assuming the maximum historical value is 50): .

[0098] The wire consumption data for the past 30 seconds is as shown in the following table:

[0099] Calculate the integral term: ; Normalization processing (theoretical value ): .

[0100] Calculation of the health compensation factor: Standardized health deviation: ; .

[0101] The first welding quality score:

[0102] The first welding quality score is greater than the first preset threshold of 0.6, indicating that the first welding quality is qualified.

[0103] S30. If the first welding quality score is less than or equal to the first preset threshold, suspend the welding task and send an alarm signal.

[0104] S40. If the first welding quality score is greater than the first preset threshold, obtain the second welding quality scores of at least one second welding segment within a preset time period.

[0105] Specifically, the second welding segment is the welded segment that has been completed. The method for obtaining the second welding quality score of the second welding segment is the same as the method for obtaining the first welding quality score of the first welding segment. Here, it is to distinguish the current welding segment from the welded segments that have been completed. Substantially, the second welding segment is dynamically changing, that is, the area to be welded is divided into multiple welding segments. The currently being welded is the first welding segment. When the first welding segment is completed, it is added to the second welding segment set.

[0106] S50. Estimate the estimated quality score of the third welding segment of the low-pressure outer cylinder that has not been welded according to all the second welding quality scores and the first welding quality score, and determine whether the estimated quality score is greater than the second preset threshold.

[0107] Optionally, the step of estimating the estimated quality score of the third welding segment of the low-pressure outer cylinder that has not been welded according to all the second welding quality scores and the first welding quality score, and determining whether the estimated quality score is greater than the second preset threshold includes: The expression for the estimated quality score of the third welding segment is:

[0108] In the formula, Represents the estimated quality score of the third weld segment, m represents the number of welded segments, k represents the index of the historical weld segment, A temporary index variable representing the normalization denominator, Represents the quality score of the k-th weld segment, Represents the attenuation coefficient, Represents the heat affected zone gradient, Represents the heat affected zone gradient coefficient, Represents the process parameter correction factor.

[0109] m represents the number of welded segments, including the first weld segment and all second weld segments.

[0110] k represents the index of the historical weld segment, , that is, successively represents the 1st to the m-th welded segments.

[0111] A temporary index variable representing the normalization denominator, Both and k represent the indices of the welded segments (from 1 to m), traversing all historical data. K is bound to a specific weld segment in the numerator to calculate its score contribution, In the denominator, it is only used for summation calculation, not directly associated with a specific weld segment, and is a local variable in the mathematical expression.

[0112] Represents the attenuation coefficient, which determines the attenuation rate of the influence of the historical weld segment quality score on the current estimated score over time (weld segment order).

[0113] , giving higher weights to recent weld segments, with the weights decaying according to decay, reflecting the temporal continuity of the welding process, and the recent process state has a greater impact on the prediction.

[0114] By performing a weighted average of the historical weld segment quality scores, the historical weld segments closer to the current estimated weld segment have a greater impact on the estimated score, while the more distant historical weld segments have a smaller impact. This can make more reasonable use of historical welding data and reflect the trend of quality changes during the welding process.

[0115] Represents the heat affected zone gradient, which reflects the change in the influence of the heat affected zone on the welding quality during the welding process. For example, during welding, temperature changes and microstructure transformations in the heat affected zone will affect the quality of the weld seam, and the heat affected zone gradient can be obtained by analyzing and calculating the temperature field, stress field, etc. in the welding area.

[0116] The expression of is .

[0117] In the formula represents the mass gradient, which is used to calculate the mass change rate per unit length of adjacent welding segments and reflects the welding heat accumulation effect: if the mass of the last segment drops rapidly, it indicates that there is an abnormality in the heat affected zone (HAZ).

[0118] represents the attenuation factor, which is exponentially attenuated by the gradient according to the distance d and conforms to the law of heat conduction. The farther the distance, the smaller the influence.

[0119] represents the heat affected zone gradient coefficient, which is used to adjust the influence degree of the heat affected zone gradient on the predicted quality score. According to the characteristics of the welding process and the importance of the heat affected zone, the value can be adjusted. For example, if the heat affected zone has a greater impact on the welding quality, the value can be appropriately increased.

[0120] Considering the influence of the heat affected zone on the welding quality, by introducing the heat affected zone gradient and the corresponding coefficient, the predicted quality score can more accurately reflect the heat influence factors in the welding process and improve the accuracy of the prediction.

[0121] For : represents different categories of process parameters. For example, may represent the welding current, represents the welding voltage, represents the substrate temperature gradient, represents the environmental humidity, etc.

[0122] is the process parameter correction factor, which corrects the predicted quality score according to the specific process parameter value . The calculation of the correction factor can be obtained from experimental data, empirical formulas or theoretical models. For example, for the welding current , if the welding current is within the appropriate range, the value is close to 1; if the welding current is too large or too small, the value will decrease accordingly to reflect the negative impact of the welding current on the welding quality.

[0123]

[0124] In the formula, represents the theoretical optimal value, represents the theoretical maximum value.

[0125] When the parameter deviates from the optimal value When the score decays according to the square relationship, strengthen the restraint of process discipline: minor deviations result in minor deductions, while major deviations result in severe penalties (e.g., a current deviation of ±8% results in a 64% deduction).

[0126] When it exceeds the limit, the correction factor is forced to be set to 0.2 to avoid unreasonable predictions under extreme working conditions and trigger the parameter reconstruction mechanism.

[0127] Joint correction of multiple parameters (current, gas, humidity, temperature gradient) to conform to the multi-factor coupling characteristics of welding quality.

[0128] Considering the influence of process parameters on welding quality, by correcting different process parameters, the predicted quality score can more accurately reflect the quality under actual welding process conditions. Different combinations of process parameters will lead to changes in welding quality. By introducing a process parameter correction factor, the predicted score can be finely adjusted.

[0129] S60. If the predicted quality score is less than or equal to the second preset threshold, adjust the welding strategy.

[0130] Optionally, if the predicted quality score is greater than the second preset threshold, it indicates that the expected quality of the unwelded weld segment meets the requirements. Do not change the welding strategy and continue welding according to the original welding strategy.

[0131] Optionally, the step of adjusting the welding strategy if the predicted quality score is less than or equal to the second preset threshold includes: Perform at least any one of the following operations: S601. According to the key parameter deviation that causes the insufficient predicted quality score, correct the welding process parameters in real time; Optionally, first determine which welding process parameters have the greatest impact on the predicted quality score. For example, welding current, welding voltage, welding speed, wire extension length, etc. By comparing the actual welding process parameters with the preset optimal parameter range, find the parameters with large deviations.

[0132] Use data analysis tools, such as statistical process control (SPC) charts, to analyze the historical data and current data of these parameters to determine the trend and degree of deviation. For example, if it is found that the welding current continuously falls below the optimal range and the deviation value is large, then the welding current is one of the key parameters that cause the insufficient predicted quality score.

[0133] According to the magnitude and direction of the key parameter deviation, adjust the control parameters of the welding equipment in real time. For example, if the welding current is low, the output current of the welding power source can be increased to correct it; if the welding speed is too fast, the moving speed of the welding trolley can be reduced.

[0134] Establish a feedback mechanism for parameter correction to ensure that the corrected parameters can be reflected in the welding process in real time. For example, use sensors to monitor the changes in welding parameters in real time and feed the data back to the control system. The control system adjusts the parameters in a timely manner according to the feedback information. Continuously monitor the corrected welding process and evaluate the correction effect. If the predicted quality score is still insufficient, it is necessary to further analyze the reasons and adjust the correction strategy.

[0135] S602. Weaken the decline in welding quality caused by equipment failures or component aging; Optionally, conduct a comprehensive inspection of the welding equipment, including the electrical system, mechanical system, control system, etc. Use professional detection tools and methods, such as vibration analysis, infrared thermal imaging, electrical performance testing, etc., to timely detect signs of equipment failures and component aging. Establish a database for equipment failures and component aging, and record information such as the type, occurrence time, and impact degree of failures and aging. Through the analysis of the database, predict possible failures and aging problems and take preventive measures in advance.

[0136] For equipment failures, repair and replace the faulty components in a timely manner. During the repair process, strictly operate according to the equipment manufacturer's repair manual to ensure the repair quality. For component aging, formulate a reasonable replacement plan based on the service life and performance status of the components. When replacing components, select components with reliable quality and stable performance to ensure the normal operation of the equipment.

[0137] Optimize the welding process to reduce the dependence on equipment performance. For example, adjust the welding parameters to reduce the requirements for equipment accuracy and stability; adopt redundant design so that when a certain component fails, other components can continue to work to ensure the continuity of the welding process.

[0138] S603. Reduce welding defects caused by spatial positions through path planning or operation correction; Optionally, conduct a detailed analysis of the spatial position of the welded workpiece to determine possible welding difficulties and defect-prone areas. For example, for workpieces with complex structures, there may be problems such as narrow spaces and poor welding angles in some parts. Use 3D modeling software to simulate the welding process and predict the welding quality at different spatial positions. Through the simulation results, identify the areas that need to be focused on and the types of defects that may occur.

[0139] Optimize the welding path according to the spatial position analysis results. For example, adjust the movement trajectory of the welding robot to avoid complex operations in narrow spaces; adopt multi-pass welding technology to reduce the thickness of single-pass welding and lower the welding difficulty.

[0140] During the welding process, monitor the welding quality in real time. When welding defects caused by spatial position are found, adjust the welding path or operation method in a timely manner. For example, use a weld tracking system to automatically adjust the welding path to ensure the forming quality of the weld.

[0141] S604. Forcefully pause the welding task and initiate the manual intervention process.

[0142] Optionally, clarify the conditions for forcefully pausing the welding task, such as the estimated quality score being lower than a certain specific critical value, the occurrence of serious equipment failures or safety hazards, etc. These conditions can be set according to the requirements of the welding process and quality standards.

[0143] Set corresponding alarm and pause mechanisms in the welding control system. When the pause conditions are met, the system automatically sends an alarm signal and pauses the welding task.

[0144] After the welding task is paused, immediately initiate the manual intervention process. Notify relevant technicians and quality management personnel to arrive at the scene for a comprehensive assessment of the welding situation.

[0145] Technicians check and debug the welding equipment to eliminate equipment failures; quality management personnel analyze the welding quality to determine the reasons for the insufficient estimated quality score.

[0146] Based on the assessment results, formulate corresponding solutions. If it is necessary to adjust welding process parameters, replace equipment components, or modify the welding path, etc., operate according to the corresponding procedures.

[0147] After the problem is solved, re - debug and conduct a trial run of the welding equipment. After ensuring that the welding quality meets the requirements, resume the welding task.

[0148] Embodiment 3 Based on Embodiment 1, this embodiment provides a low - pressure outer cylinder welding quality monitoring system, including: A characteristic parameter acquisition module configured to acquire welding characteristic parameters of a first welding segment within a preset time period, where the welding characteristic parameters include at least one of weld image information, arc sound signal, wire consumption information, and welding equipment stability coefficient; A first welding quality score acquisition module configured to evaluate a first welding quality score of the first welding segment based on the welding characteristic parameters using a welding quality assessment model and determine whether the first welding quality score is greater than a first preset threshold; If not, pause the welding task and send an alarm signal; If so, acquire a second welding quality score of at least one second welding segment within a preset time period; An estimated quality score acquisition module, which is configured to estimate the estimated quality score of the third welded section that has not been welded on the low-pressure outer cylinder according to all the second welding quality scores and the first welding quality score, and determine whether the estimated quality score is greater than a second preset threshold; A welding strategy adjustment module, which is configured to adjust the welding strategy if the estimated quality score is less than or equal to the second preset threshold.

[0149] Embodiment 4 This embodiment provides a computer device, including a memory and a processor. A computer program that can run on the processor is stored on the memory. When the processor executes the computer program, it implements the low-pressure outer cylinder welding quality monitoring method as described above in any one of the preceding embodiments.

[0150] Embodiment 5 This embodiment provides a computer-readable storage medium, storing a computer program that can be loaded and executed by a processor to implement the low-pressure outer cylinder welding quality monitoring method as described above.

[0151] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disc, or CD-ROM; or it may be various devices including one or any combination of the above memories. The computer may be various computing devices including smart terminals and servers.

[0152] In the above embodiments of the present disclosure, the descriptions of each embodiment have their own emphases. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0153] In the several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of units can be a logical function division. In actual implementation, there may be other division methods. 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, the couplings or direct couplings or communication connections shown or discussed with each other can be through some interfaces. The indirect couplings or communication connections of units or modules can be electrical or other forms.

[0154] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, in each of the embodiments of the present disclosure, the functional units may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0156] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable non-volatile storage medium. Based on such an understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product. The computer software product is stored in a non-volatile storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present disclosure. The aforementioned non-volatile storage medium includes: various media such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0157] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structural or equivalent process transformation made by using the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A method for monitoring the welding quality of a low-pressure outer cylinder, characterized in that including: Obtain the welding characteristic parameters of the first welding section within a preset time period, where the welding characteristic parameters include at least one of weld seam image information, arc sound signal, wire consumption information, and welding equipment stability coefficient; Based on the welding characteristic parameters, evaluate the first welding quality score of the first welding section based on a welding quality evaluation model, and determine whether the first welding quality score is greater than a first preset threshold; If not, pause the welding task and issue an alarm signal; If so, obtain the second welding quality scores of at least one second welding section within the preset time period; Based on all the second welding quality scores and the first welding quality score, estimate the estimated quality score of the third welding section of the low-pressure outer cylinder that has not been welded, and determine whether the estimated quality score is greater than a second preset threshold; If the estimated quality score is less than or equal to the second preset threshold, adjust the welding strategy.

2. The method for monitoring the welding quality of the low-pressure outer cylinder according to claim 1, wherein The step of evaluating the first welding quality score of the first welding section based on the welding characteristic parameters according to the welding quality evaluation model and determining whether the first welding quality score is greater than the first preset threshold includes: The expression of the welding quality evaluation model is: In the formula, represents the first welding quality score, represents the image feature item, represents the weight coefficient of the image feature item, represents the acoustic feature item, represents the weight coefficient of the acoustic feature item, represents the wire consumption item, represents the weight coefficient of the wire consumption item, represents the health compensation gain coefficient, represents the current stability coefficient of the welding equipment, represents the mean value of the historical stability coefficients of the welding equipment, represents the standard deviation of the historical stability coefficients of the welding equipment.

3. The low-pressure outer cylinder welding quality monitoring method according to claim 2, characterized in that The expression of the image feature term is: In the formula, represents the area of the weld region, represents the gray value at time t at the point (x, y) in the weld region, represents the standard deviation of the Gaussian kernel, represents the weld region, represents the two-dimensional convolution operation symbol, represents the Laplace operator, represents the ReLU function.

4. The method for monitoring the welding quality of the low-pressure outer cylinder according to claim 2, characterized in that, The expression of the acoustic feature term is: In the formula, B represents the bandwidth normalization factor, and represents the characteristic frequency range, represents the time-domain signal of the arc sound, represents the short-time Fourier transform operator, represents the short-time Fourier transform; represents the complex value at frequency f in the spectrum corresponding to time point t; represents the imaginary unit, represents the acoustic wave propagation time delay compensation, used to correct the phase shift caused by the acoustic wave propagation time delay, represents the frequency variable.

5. The method for monitoring the welding quality of a low-pressure outer cylinder according to claim 2, wherein, The expression of the wire consumption term is: In the formula, represents the length of the monitoring time window, represents the decay constant, represents at time the total consumption of the welding wire, represents at time the instantaneous consumption rate, represents the current time point, represents the time integral variable.

6. The method for monitoring the welding quality of a low-pressure outer cylinder according to claim 1, characterized in that The step of estimating the estimated quality score of the third welding section of the low-pressure outer cylinder that has not been welded based on all the second welding quality scores and the first welding quality score and determining whether the estimated quality score is greater than the second preset threshold includes: The expression of the estimated quality score of the third welding section is: Wherein, m represents the number of welded weld segments, and k represents the index of the historical weld segment. A temporary index variable representing the normalization denominator. Represents the quality score of the k-th weld segment. Represents the attenuation coefficient. Represents the heat affected zone gradient. Represents the heat affected zone gradient coefficient. Represents the process parameter correction factor.

7. The method for monitoring the welding quality of the low-pressure outer cylinder according to claim 1, characterized in that, The step of adjusting the welding strategy if the estimated quality score is less than or equal to the second preset threshold includes: Perform at least any one of the following operations: According to the key parameter deviation that causes the insufficient estimated quality score, correct the welding process parameters in real time; Weaken the decrease in welding quality caused by equipment failure or component aging; Reduce welding defects caused by spatial position through path planning or operation correction; Forcefully pause the welding task and start the manual intervention process.

8. A welding quality monitoring system for a low-pressure outer cylinder, characterized in that including: A feature parameter acquisition module configured to obtain the welding characteristic parameters of the first welding section within a preset time period, where the welding characteristic parameters include at least one of weld seam image information, arc sound signal, wire consumption information, and welding equipment stability coefficient; A first welding quality score acquisition module configured to evaluate the first welding quality score of the first welding section based on the welding characteristic parameters according to the welding quality evaluation model and determine whether the first welding quality score is greater than the first preset threshold; If not, pause the welding task and issue an alarm signal; If so, obtain the second welding quality scores of at least one second welding section within the preset time period; An estimated quality score acquisition module configured to estimate the estimated quality score of the third welding section of the low-pressure outer cylinder that has not been welded based on all the second welding quality scores and the first welding quality score and determine whether the estimated quality score is greater than the second preset threshold; A welding strategy adjustment module configured to adjust the welding strategy if the estimated quality score is less than or equal to the second preset threshold.

9. A computer device, characterized in that, It includes a memory and a processor. A computer program that can run on the processor is stored on the memory. When the processor executes the computer program, it implements the low-pressure outer cylinder welding quality monitoring method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Stores a computer program that can be loaded and executed by a processor to implement the low-pressure outer cylinder welding quality monitoring method according to any one of claims 1 to 7.

Images