Welding quality monitoring method and system for plastic liner welding machine

Abstract

The invention discloses a welding quality monitoring method and system for a plastic liner welding machine, belongs to the technical field of plastic liner welding, and aims to solve the technical problems that the welding quality of plastic liners is uneven, parameters cannot be quickly adjusted to the most favorable degree for improving the product welding qualification rate, and the production efficiency of the plastic liners is affected. The method comprises the steps that an image detection model and a welding quality detection model based on an X-ray image are constructed and trained; performing basic quality detection on welding products of the plastic liner welding machine one by one through the image detection model; under the condition that the basic quality detection reaches a preset condition, X-ray detection is conducted on the current welding product, and an X-ray image is obtained; inputting the X-ray image into a welding quality detection model to obtain the welding strength of the current welding product; and on the basis of the basic quality detection result and the welding strength detection result in the preset time period, the to-be-adjusted welding node and the corresponding adjustment parameters are determined.

Description

Technical Field

[0001] The present invention relates to the technical field of plastic inner liner welding, and particularly to a welding quality monitoring method and system for a plastic inner liner welding machine. Background Art

[0002] Hydrogen is a green and efficient clean energy. Type IV hydrogen storage cylinders have become the main field of hydrogen energy research and development applications due to their light weight, fatigue resistance, high hydrogen storage density per unit mass, etc. However, limited by the existing processing technology, it is almost impossible to form a large aspect ratio and large-capacity thin-walled plastic inner liner in one processing. Therefore, it is necessary to perform multiple two-stage weldings on the injection-molded inner liner of the Type IV cylinder by heating and welding to finally form a complete inner liner.

[0003] At present, there are already relatively mature plastic inner liner welding machines and welding production lines. However, plastic inner liner welding is affected by factors such as welding temperature, heating time, heating method, welding pressure, etc. The final welding quality is uneven, and the qualified rate of product welding is often unsatisfactory. Although the parameters of each welding link can be adjusted manually to improve the qualified rate of product welding as much as possible, this method is inefficient and cannot quickly adjust each welding link to the most favorable degree for improving the qualified rate of product welding. It is necessary to repeatedly debug to obtain better adjustment parameters, and many unqualified welding products will appear during this period, affecting the production efficiency and causing losses of interests at the same time. Summary of the Invention

[0004] Embodiments of the present invention provide a welding quality monitoring method and system for a plastic inner liner welding machine to solve the following technical problems: Plastic inner liner welding is affected by various factors, the welding quality is uneven, and it is necessary to repeatedly debug the parameters of each welding link, and the parameters cannot be quickly adjusted to the most favorable degree for improving the qualified rate of product welding, affecting the production efficiency of plastic inner liners.

[0005] Embodiments of the present invention adopt the following technical solutions:

[0006] On the one hand, embodiments of the present invention provide a welding quality monitoring method for a plastic inner liner welding machine, and the method includes: constructing an image detection model and a welding quality detection model based on X-ray images and training them;

[0007] Performing basic quality detection on each welding product of the plastic inner liner welding machine through the image detection model; wherein, the basic quality detection at least includes misalignment amount detection and weld width detection;

[0008] In the case that the basic quality detection reaches a preset condition, performing X-ray detection on the current welding product to obtain an X-ray image;

[0009] Input the X-ray image into the welding quality detection model to obtain the welding strength of the current welded product;

[0010] Based on the basic quality detection results and welding strength detection results of all welded products detected within a preset time period, determine the welding nodes to be adjusted and the corresponding adjustment parameters;

[0011] Perform corresponding adjustments on the welding nodes to be adjusted through the adjustment parameters to improve the welding quality.

[0012] In a feasible implementation manner, construct an image detection model and a welding quality detection model based on X-ray images and perform training, specifically including:

[0013] Construct an X-ray image dataset of the plastic inner liner welding part, and perform defect annotation on the images in the X-ray image dataset;

[0014] Construct a densely connected convolutional network with a preset number of convolutional layers, and add transition layers between each convolutional layer to form an initial welding quality detection model; wherein, the transition layer includes a batch normalization operation and an average pooling layer;

[0015] Train the initial welding quality detection model through the annotated X-ray image dataset to obtain a welding quality detection model based on X-ray images;

[0016] Construct a general image dataset of the plastic inner liner welding part;

[0017] Based on the YOLO model, construct a basic image detection model and perform model training through the general image dataset.

[0018] In a feasible implementation manner, construct an X-ray image dataset of the plastic inner liner welding part, and perform defect annotation on the images in the X-ray image dataset, specifically including:

[0019] Collect X-ray images of several plastic inner liner welding samples through an X-ray imaging device, and perform image expansion to form the X-ray image dataset;

[0020] Conduct tensile tests on the plastic inner liner welding samples and record the weld fracture time of each plastic inner liner welding sample;

[0021] Based on the ratio between the weld fracture time and the standard value, convert the weld fracture time into a welding strength value;

[0022] Using a labeling software, defect labeling is performed on each X-ray image in the X-ray image dataset; wherein, the types of labeled defect parts at least include: porosity parts, crack parts, slag inclusion parts, foreign object parts, and lack of fusion parts;

[0023] Associate the welding strength value with the labeled X-ray image to form the final X-ray image dataset.

[0024] In a feasible implementation manner, the basic quality of the welding products of the plastic inner liner welding machine is detected one by one through an image detection model, specifically including:

[0025] On the plastic inner liner welding production line, through an image acquisition device installed at a preset position, the welding part image of the welding product is scanned circumferentially 360 degrees to obtain the welding part image of the welding product;

[0026] Input the welding part images into the image detection model one by one for basic quality detection to obtain the basic quality detection results; wherein, the basic quality detection results at least include the misalignment amount and the weld width.

[0027] In a feasible implementation manner, when the basic quality detection meets the preset conditions, X-ray detection is performed on the current welding product to obtain an X-ray image, specifically including:

[0028] Calculate the first difference between the misalignment amount of the current welding product and the normal misalignment amount, and the second difference between the weld width of the current welding product and the normal weld width respectively;

[0029] If any one of the first difference and the second difference exceeds its corresponding preset threshold, trigger X-ray detection on the current welding product, and collect the X-ray image of the current welding product through the X-ray imaging device installed on the plastic inner liner welding production line.

[0030] In a feasible implementation manner, based on the basic quality detection results and welding strength detection results of all welding products detected within a preset time period, determine the welding nodes to be adjusted and the corresponding adjustment parameters, specifically including:

[0031] Based on the basic quality detection results of all welding products detected within a preset time period, calculate the average misalignment amount and the average weld width;

[0032] Based on the welding strength detection results of the welding products that trigger X-ray detection within a preset time period, calculate the average welding strength;

[0033] Calculate the differences between the average misalignment amount, the average weld width, and the average welding strength and their corresponding normal values respectively;

[0034] If any of the differences is greater than the set adjustment threshold of the welding machine, determine the adjustment parameters for the corresponding welding node.

[0035] In a feasible implementation manner, if any of the differences is greater than the set adjustment threshold of the welding machine, determine the adjustment parameters for the corresponding welding node, specifically including:

[0036] If the difference between the average misalignment amount and the normal misalignment amount is greater than the first adjustment threshold, determine the first misalignment direction and the second misalignment direction of the welding machine correction mechanism according to the misalignment amount detection results within the preset time period; wherein, the first misalignment direction is inward misalignment or outward misalignment; the second misalignment direction is upward misalignment or downward misalignment;

[0037] Statistically analyze the average horizontal misalignment amount in the first misalignment direction and the average vertical misalignment amount in the second misalignment direction;

[0038] Generate the first reference position adjustment value of the welding machine correction mechanism based on the difference between the average horizontal misalignment amount and the normal horizontal misalignment amount;

[0039] Generate the second reference position adjustment value of the welding machine correction mechanism based on the difference between the average vertical misalignment amount and the normal vertical misalignment amount.

[0040] In a feasible implementation manner, if any of the differences is greater than the set adjustment threshold of the welding machine, determine the adjustment parameters for the corresponding welding node, specifically further including:

[0041] If the difference between the average weld width and the normal weld width is greater than the second adjustment threshold, determine the adjustment value of the pressing force of the welding machine pressing mechanism according to the ratio of the difference to the normal weld width and the current pressing force of the welding machine pressing mechanism.

[0042] In a feasible implementation manner, if any of the differences is greater than the set adjustment threshold of the welding machine, determine the adjustment parameters for the corresponding welding node, specifically further including:

[0043] If the difference between the average welding strength and the normal welding strength is greater than the third adjustment threshold, determine the adjustment value of the heating temperature of the welding machine heating mechanism according to the ratio of the difference to the normal welding strength and the current heating temperature of the welding machine heating mechanism; and,

[0044] Determine the adjustment value of the pressing force of the welding machine pressing mechanism according to the ratio of the difference to the normal welding strength and the current pressing force of the welding machine pressing mechanism.

[0045] On the other hand, an embodiment of the present invention further provides a welding quality monitoring system for a plastic inner liner welding machine, and the system includes:

[0046] A model construction module, configured to construct an image detection model and a welding quality detection model based on X-ray images and perform training;

[0047] A basic quality detection module, configured to perform basic quality detection on each welding product of the plastic inner liner welding machine through the image detection model; wherein, the basic quality detection at least includes misalignment detection and weld width detection;

[0048] A depth quality detection module, configured to perform X-ray detection on the current welding product to obtain an X-ray image when the basic quality detection reaches a preset condition; input the X-ray image into the welding quality detection model to obtain the welding strength of the current welding product;

[0049] A welding node adjustment module, configured to determine a welding node to be adjusted and corresponding adjustment parameters based on the basic quality detection results and welding strength detection results of all welding products detected within a preset time period; perform corresponding adjustment on the welding node to be adjusted through the adjustment parameters to improve the welding quality.

[0050] Compared with the prior art, a welding quality monitoring method and system for a plastic inner liner welding machine provided by an embodiment of the present invention have the following beneficial effects:

[0051] The present invention comprehensively detects the welding quality of products welded by a plastic inner liner welding machine through image processing technology and X-ray detection technology, and based on different detection parameters, finely adjusts the parameters of each welding mechanism of the welding machine. Thus, it can quickly adjust each welding link to the most favorable degree for improving the welding qualification rate of products, and does not require repeated debugging. It can quickly detect the welding link defects of the welding machine according to the product quality feedback and make corresponding adjustments, reducing the unqualified rate of welding products and improving the production efficiency of plastic inner liners. Description of the Drawings

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments recorded in the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In the drawings:

[0053] Figure 1 It is a flowchart of a welding quality monitoring method for a plastic inner liner welding machine provided by an embodiment of the present invention;

[0054] Figure 2 This is a schematic structural diagram of a welding quality monitoring system for a plastic inner liner welding machine provided by an embodiment of the present invention. Specific embodiments

[0055] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention 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 this specification, 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.

[0056] An embodiment of the present invention provides a method for monitoring the welding quality of a plastic inner liner welding machine. As Figure 1 shown, the method for monitoring the welding quality of a plastic inner liner welding machine specifically includes steps S101 - S105:

[0057] S101. Construct an image detection model and a welding quality detection model based on X - ray images and perform training.

[0058] Specifically, first construct an X - ray image dataset of the welding part of the plastic inner liner, and perform defect annotation on the images in the X - ray image dataset.

[0059] As a feasible implementation method, the specific construction process of the X - ray image dataset is as follows:

[0060] First, through an X - ray imaging device, collect X - ray images of several plastic inner liner welding samples and perform image expansion to form an X - ray image dataset. In the present invention, the directly collected X - ray images are respectively subjected to operations such as rotation, horizontal and vertical movement, shear transformation, magnification, and horizontal flipping. The transformation coefficients of all operations are randomly generated within a certain range. Among them, there is no transformation range for horizontal flipping, and the probability of occurrence is 0.5.

[0061] Then, perform tensile tests on these plastic inner liner welding samples and record the weld fracture time of each plastic inner liner welding sample. Calculate the ratio between the weld fracture time of each sample and the standard value, and use this ratio as the welding strength value of the plastic inner liner welding sample.

[0062] Furthermore, through annotation software, perform defect annotation on each X - ray image in the X - ray image dataset; among them, the types of defect parts to be annotated at least include: pore parts, crack parts, slag inclusion parts, foreign object parts, and lack - of - fusion parts. Finally, associate the welding strength value with the annotated X - ray images to form the final X - ray image dataset.

[0063] Further, a densely connected convolutional network with a preset number of convolutional layers is constructed, and a transition layer is added between each convolutional layer to form an initial welding quality detection model; wherein, the transition layer includes a batch normalization operation and an average pooling layer. Then, the initial welding quality detection model is trained through the labeled X-ray image dataset to obtain a welding quality detection model based on X-ray images.

[0064] Further, a general image dataset of the welded parts of the plastic inner liner is constructed. The general image dataset is a dataset formed by taking circumferential 360-degree scanned images of the welded parts of plastic inner liners with different welding qualities.

[0065] Further, based on the YOLO model, a basic image detection model is constructed and the model is trained through the general image dataset.

[0066] S102. Perform basic quality inspections on the welded products of the plastic inner liner welding machine one by one through the image detection model; wherein, the basic quality inspection includes at least misalignment detection and weld width detection.

[0067] Specifically, on the plastic inner liner welding production line, the welded products are scanned circumferentially 360 degrees through an image acquisition device installed at a preset position to obtain the welded part images of the welded products. Then, the welded part images are input into the image detection model one by one for basic quality inspection to obtain basic quality inspection results; wherein, the basic quality inspection results include at least misalignment and weld width.

[0068] As a feasible implementation manner, the misalignment is the offset amount that appears at the edge or surface of two materials being welded during the welding process. It may be due to the deviation of the reference position, and there is a situation where the two materials are not aligned horizontally or vertically. Therefore, the misalignment here includes horizontal misalignment and vertical misalignment. In the present invention, the misaligned position of the welded product is scanned circumferentially 360 degrees, and the maximum misalignment width of the entire misaligned position is monitored as the misalignment amount. At the same time, the cross-sectional area of the protrusion at the weld is also monitored, and the cross-sectional area of the protrusion can be combined with the misalignment amount to determine whether the basic welding quality is qualified.

[0069] S103. When the basic quality inspection meets the preset conditions, perform X-ray inspection on the current welded product to obtain an X-ray image. The X-ray image is input into the welding quality detection model to obtain the welding strength of the current welded product.

[0070] Specifically, calculate the first difference between the misalignment amount of the current welded product and the normal misalignment amount, and the second difference between the weld width of the current welded product and the normal weld width.

[0071] If any one of the first difference and the second difference exceeds its corresponding preset threshold, X-ray inspection is triggered for the current welded product, and an X-ray image of the current welded product is collected by the X-ray imaging device installed on the plastic inner liner welding production line.

[0072] Then the X-ray image is input into the welding quality inspection model to obtain the welding strength of the current welded product.

[0073] S104. Based on the basic quality inspection results and welding strength inspection results of all welded products detected within a preset time period, determine the welding nodes to be adjusted and the corresponding adjustment parameters.

[0074] Specifically, based on the basic quality inspection results of all welded products detected within a preset time period, calculate the average misalignment amount and the average weld width.

[0075] Further, based on the welding strength inspection results of the welded products for which X-ray inspection is triggered within a preset time period, calculate the average welding strength.

[0076] Then calculate the differences between the average misalignment amount, the average weld width, and the average welding strength and their corresponding normal values respectively. If any difference is greater than the set welding machine adjustment threshold, determine the adjustment parameters for the corresponding welding node.

[0077] As a specific implementation manner, if the difference between the average misalignment amount and the normal misalignment amount value is greater than the first adjustment threshold, determine the first misalignment direction and the second misalignment direction of the welding machine correction mechanism according to the misalignment amount inspection results within the preset time period; wherein, the first misalignment direction is inward misalignment or outward misalignment; the second misalignment direction is upward misalignment or downward misalignment.

[0078] Then count the average horizontal misalignment amount in the first misalignment direction and the average vertical misalignment amount in the second misalignment direction. Generate the first reference position adjustment value of the welding machine correction mechanism based on the difference between the average horizontal misalignment amount and the normal horizontal misalignment amount value. Generate the second reference position adjustment value of the welding machine correction mechanism based on the difference between the average vertical misalignment amount and the normal vertical misalignment amount value.

[0079] In one embodiment, if the average misalignment amount exceeds the normal value by a large margin, it proves that the alignment of the calibration mechanism of the welding machine is not precise enough and needs to be adjusted. At this time, since the inner tank material to be welded has two sides, namely the inner side and the outer side, first, according to the misalignment amount detection result, it is statistically determined whether material A shifts inward or outward of material B among the two pieces of material. If A shifts inward of B, the first misalignment direction is inward misalignment; if A shifts outward of B, the first misalignment direction is outward misalignment. And if the upper and lower edges of A and B are not aligned, if the upper edge of A is higher than B, then the second misalignment direction is upward misalignment; if the upper edge of A is lower than B, then the second misalignment direction is downward misalignment. After determining the misalignment direction, the difference between the average misalignment amount of the welded products with the same misalignment direction and the normal value is determined as the calibration adjustment value in this direction.

[0080] As a second specific implementation manner, if the difference between the average weld width and the normal weld width value is greater than the second adjustment threshold, the pressing force adjustment value of the pressing mechanism of the welding machine is determined according to the ratio between the difference and the normal weld width value, and the current pressing force of the pressing mechanism of the welding machine.

[0081] In one embodiment, if the difference between the average weld width and the normal value is relatively high, the current pressing force of the pressing mechanism of the welding machine is multiplied by the ratio between the difference and the normal value to obtain the additional pressing force adjustment value that needs to be increased.

[0082] As a third specific implementation manner, if the difference between the average welding strength and the normal welding strength value is greater than the third adjustment threshold, the heating temperature adjustment value of the heating mechanism of the welding machine is determined according to the ratio between the difference and the normal welding strength value, and the current heating temperature of the heating mechanism of the welding machine; and, the pressing force adjustment value of the pressing mechanism of the welding machine is determined according to the ratio between the difference and the normal welding strength value, and the current pressing force of the pressing mechanism of the welding machine.

[0083] In one embodiment, the welding strength is related to both the heating temperature and the pressing force during welding. Therefore, by multiplying the actual parameters of the current mechanism by the ratio of the difference in welding strength to the normal value, the heating temperature adjustment value of the heating mechanism and the pressing force adjustment value of the pressing mechanism are respectively obtained.

[0084] S105. Corresponding adjustments are made to the welding nodes to be adjusted by adjusting the parameters to improve the welding quality.

[0085] Specifically, after obtaining the adjustment parameters in S104, parameter adjustment is performed on the welding nodes that need to be adjusted. For example, if the average value of the weld width exceeds the normal value among all the welded products detected within 5 hours, the difference between the two is calculated, and the pressing force adjustment value is calculated. Then, based on the current pressing force of the pressing mechanism of the welding machine, this pressing force adjustment value is added to obtain the adjusted pressing force, which is applied to the pressing mechanism to improve the weld width of subsequent products.

[0086] In addition, the embodiment of the present invention also provides a welding quality monitoring system for a plastic inner liner welding machine, as Figure 2 shown. The welding quality monitoring system 200 of the plastic inner liner welding machine specifically includes:

[0087] A model construction module, configured to construct an image detection model and a welding quality detection model based on X-ray images and perform training;

[0088] A basic quality detection module, configured to perform basic quality detection on the welded products of the plastic inner liner welding machine one by one through the image detection model; wherein, the basic quality detection at least includes misalignment detection and weld width detection;

[0089] A depth quality detection module, configured to perform X-ray detection on the current welded product to obtain an X-ray image when the basic quality detection reaches a preset condition; input the X-ray image into the welding quality detection model to obtain the welding strength of the current welded product;

[0090] A welding node adjustment module, configured to determine the welding nodes to be adjusted and the corresponding adjustment parameters based on the basic quality detection results and welding strength detection results of all the welded products detected within a preset time period; perform corresponding adjustment on the welding nodes to be adjusted through the adjustment parameters to improve the welding quality.

[0091] Each embodiment in the present invention is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments. In particular, for the embodiments of the device, equipment, and non-volatile computer storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0092] The above describes specific embodiments of the present invention. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0093] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various modifications and variations can be made to the embodiments of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for monitoring welding quality of a plastic liner welding machine, characterized in that: The method comprises: Build and train image detection models and welding quality detection models based on X-ray images; The basic quality inspection of the welding products of the plastic liner welding machine is performed one by one through the image detection model; wherein the basic quality inspection at least includes the detection of the misalignment amount and the detection of the weld width; When the basic quality inspection meets the preset conditions, an X-ray inspection is performed on the current welding product to obtain an X-ray image; Inputting the X-ray image into the welding quality detection model to obtain the welding strength of the current welding product; Determine the welding nodes to be adjusted and the corresponding adjustment parameters based on the basic quality test results and welding strength test results of all welding products tested within a preset time period; The welding node to be adjusted is adjusted accordingly through the adjustment parameters to improve the welding quality.

2. The welding quality monitoring method of a plastic liner welding machine according to claim 1 is characterized in that: Build and train image detection models and welding quality detection models based on X-ray images, including: Constructing an X-ray image dataset of a plastic liner welding portion, and annotating defects of images in the X-ray image dataset; Constructing a densely connected convolutional network with a preset number of convolutional layers, and adding a transition layer between each convolutional layer to form an initial welding quality detection model; wherein the transition layer includes a batch normalization operation and an average pooling layer; Training the initial welding quality detection model by using the labeled X-ray image data set to obtain a welding quality detection model based on X-ray images; Construct a common image dataset of plastic liner welding parts; Based on the YOLO model, a basic image detection model is constructed, and the model is trained using the common image dataset.

3. The welding quality monitoring method of a plastic liner welding machine according to claim 2 is characterized in that: Constructing an X-ray image dataset of the welding part of the plastic liner and annotating defects of the images in the X-ray image dataset, specifically including: Using an X-ray imaging device, collecting X-ray images of a plurality of plastic liner welding samples, and performing image expansion to form the X-ray image data set; Performing a tensile test on the plastic liner welding samples, and recording the weld fracture time of each plastic liner welding sample; converting the weld rupture time into a welding strength value based on a ratio between the weld rupture time and a standard value; By using annotation software, defects are annotated in each X-ray image in the X-ray image data set; wherein the annotated defect location types include at least: pore location, crack location, slag inclusion location, foreign matter location and unfused location; The welding strength value is associated with the annotated X-ray image to form a final X-ray image data set.

4. The welding quality monitoring method of a plastic liner welding machine according to claim 1 is characterized in that: The image detection model is used to perform basic quality inspections on the welding products of the plastic liner welding machine one by one, including: On the plastic liner welding production line, the image acquisition device installed at a preset position scans the welding product 360 degrees to obtain the welding part image of the welding product; The welding part images are input one by one into the image detection model to perform basic quality detection to obtain basic quality detection results; wherein the basic quality detection results at least include the misalignment amount and the weld width.

5. The welding quality monitoring method of a plastic liner welding machine according to claim 1, characterized in that: When the basic quality inspection meets the preset conditions, an X-ray inspection is performed on the current welding product to obtain an X-ray image, which specifically includes: Calculate respectively a first difference between the misalignment amount of the current welding product and the normal misalignment amount, and a second difference between the weld seam width of the current welding product and the normal weld seam width; If any one of the first difference and the second difference exceeds the corresponding preset threshold, X-ray detection is triggered for the current welding product, and an X-ray image of the current welding product is collected by an X-ray imaging device installed on the plastic liner welding assembly line.

6. The welding quality monitoring method of a plastic liner welding machine according to claim 1, characterized in that: Based on the basic quality test results and welding strength test results of all welding products tested within a preset time period, the welding nodes to be adjusted and the corresponding adjustment parameters are determined, including: Based on the basic quality inspection results of all welding products inspected within a preset time period, the average value of the misalignment amount and the average value of the weld width are calculated; Calculate the average welding strength based on the welding strength test results of the welding products that trigger the X-ray test within a preset time period; Calculate the difference between the average value of the misalignment amount, the average value of the weld width, and the average value of the welding strength and their corresponding normal values ​​respectively; If any difference is greater than the set welding machine adjustment threshold, the adjustment parameters of the corresponding welding node are determined.

7. The method for monitoring welding quality of a plastic liner welding machine according to claim 6, characterized in that: If any difference is greater than the set welding machine adjustment threshold, the adjustment parameters of the corresponding welding node are determined, including: If the difference between the average value of the misalignment amount and the normal value of the misalignment amount is greater than the first adjustment threshold, the first misalignment direction and the second misalignment direction of the welding machine correction mechanism are determined according to the misalignment amount detection result within the preset time period; wherein the first misalignment direction is an inward misalignment or an outward misalignment; and the second misalignment direction is an upward misalignment or a downward misalignment; Calculate the average value of the horizontal misalignment in the first misalignment direction and the average value of the vertical misalignment in the second misalignment direction; Based on the difference between the average value of the horizontal misalignment and the normal value of the horizontal misalignment, a first reference position adjustment value of the welding machine correction mechanism is generated; Based on the difference between the average value of the vertical misalignment and the normal value of the vertical misalignment, a second reference position adjustment value of the welding machine correction mechanism is generated.

8. The method for monitoring welding quality of a plastic liner welding machine according to claim 6, characterized in that: If any difference is greater than the set welding machine adjustment threshold, the adjustment parameters of the corresponding welding node are determined, which specifically includes: If the difference between the average weld width value and the normal weld width value is greater than the second adjustment threshold, the clamping force adjustment value of the welding machine clamping mechanism is determined based on the ratio between the difference and the normal weld width value and the current clamping force of the welding machine clamping mechanism.

9. The method for monitoring welding quality of a plastic liner welding machine according to claim 6, characterized in that: If any difference is greater than the set welding machine adjustment threshold, the adjustment parameters of the corresponding welding node are determined, which specifically includes: If the difference between the average value of the welding strength and the normal value of the welding strength is greater than a third adjustment threshold, determining a heating temperature adjustment value of the welding machine heating mechanism according to a ratio between the difference and the normal value of the welding strength and a current heating temperature of the welding machine heating mechanism; and, According to the ratio between the difference and the normal value of the welding strength, and the current clamping force of the clamping mechanism of the welding machine, the clamping force adjustment value of the clamping mechanism of the welding machine is determined.

10. A welding quality monitoring system for a plastic liner welding machine, characterized in that: The system comprises: Model building module, used to build and train image detection models and welding quality detection models based on X-ray images; A basic quality inspection module is used to perform basic quality inspection on the welding products of the plastic liner welding machine one by one through an image detection model; wherein the basic quality inspection at least includes misalignment detection and weld width detection; A deep quality inspection module is used to perform X-ray inspection on the current welding product to obtain an X-ray image when the basic quality inspection meets the preset conditions; the X-ray image is input into the welding quality inspection model to obtain the welding strength of the current welding product; A welding node adjustment module, used to determine the welding nodes to be adjusted and the corresponding adjustment parameters based on the basic quality test results and welding strength test results of all welding products tested within a preset time period; The welding node to be adjusted is adjusted accordingly through the adjustment parameters to improve the welding quality.

Images