5m-diameter aluminum lithium alloy PMI interlayer common bottom lock bottom circular seam assembly welding method based on constant temperature control

Abstract

The invention provides a 5m-diameter aluminum lithium alloy PMI interlayer common-bottom lock bottom circular seam assembly welding method based on constant temperature control. Efficient sleeving and high-quality friction stir welding of a cylinder section and a double-layer common-bottom structure lock bottom circular seam are achieved. Firstly, an interference fit sleeving method based on the thermal expansion principle is developed, interference sleeving of the cylinder section and a lock bottom circular seam of a double-layer common-bottom structure is achieved through thermal expansion of the end of the cylinder section, and the situation that large deformation is generated in a local area of the end, and stress concentration is caused can be avoided. And then a welding method for friction stir welding heat input control based on temperature control is developed, and constant-temperature and constant-deformation control in the large-diameter aluminum lithium alloy PMI interlayer common-bottom and bottom-locking circular seam friction stir welding process is achieved.

Description

Technical Field

[0001] The invention relates to the field of manufacturing large-diameter common-bottom storage tanks, and in particular to a 5m-diameter aluminum-lithium alloy PMI sandwich common-bottom lock-bottom annular seam assembly welding method based on constant temperature control. Background Art

[0002] The diameter of the third-stage tank of the new generation of manned launch vehicles is 5m. It adopts an aluminum-lithium alloy PMI sandwich common bottom structure. The tank barrel section and the double-layer common bottom structure are assembled and stir-friction welded to form a lock bottom ring seam through a vertical assembly welding mode. The barrel section and the double-layer common bottom structure are generally interference fit, and affected by manufacturing deviations, it is very difficult to vertically assemble the barrel section and the double-layer common bottom structure to form a lock bottom ring seam. It is very easy to produce large deformation and stress concentration in the local area of ​​the end, which seriously affects the quality of stir-friction welding of the lock bottom ring seam. On the other hand, the aluminum-lithium alloy PMI sandwich common bottom structure has a thin thickness and weak compressive stiffness, and the mechanical properties and thermal properties of the aluminum-lithium alloy tank bottom and the PMI foam sandwich are very different. During the stir-friction welding process of the lock bottom ring seam, under the combined effect of large welding upsetting force and welding heat input, the welding deformation behavior of the aluminum-lithium alloy PMI sandwich common bottom structure is complex and the deformation is large. It is difficult to achieve the deformation control of this type of large-diameter aluminum-lithium alloy PMI sandwich common bottom lock bottom ring seam welding using traditional constant pressure or constant displacement stir-friction welding control methods. In order to solve the above problems, it is urgent to develop a large-diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom ring seam assembly welding method. Summary of the invention

[0003] The present invention is made to solve the above-mentioned problem, and aims to provide a 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom annular seam assembly welding method based on constant temperature control.

[0004] The present invention provides a 5m diameter aluminum-lithium alloy PMI sandwich common bottom lock bottom annular seam assembly welding method based on constant temperature control, which has the following characteristics and comprises the following steps: step 1, before the barrel section and the double-layer common bottom structure are fitted, the butt joint end of the barrel section is firstly locally heated by an induction heating method to expand the butt joint end of the barrel section, thereby completing the fitting of the barrel section and the lock bottom annular seam of the double-layer common bottom structure; step 2, after the fitting is completed, waiting for the butt joint end of the barrel section to cool and shrink, thereby achieving the interference fit fitting of the barrel section and the lock bottom annular seam of the double-layer common bottom structure; step 3, using a mobile heat source and a mobile load method to establish a finite element simulation model of friction stir welding of the lock bottom annular seam of the barrel section-double-layer common bottom structure; step 4, according to the finite element method of friction stir welding of the lock bottom annular seam of the barrel section-double-layer common bottom structure The simulation model is used to establish a data set through high-throughput calculation; step 5, based on the data set, a deep learning model of the temperature / deformation of key characteristic points inside the tank-tank surface temperature field is established; step 6, during the friction stir welding process of the barrel section and the double-layer common bottom structure lock bottom ring seam, the real-time temperature of the key observation points on the tank surface is input into the deep learning model of the temperature / deformation of key characteristic points inside the tank-tank surface temperature field, so as to provide real-time feedback on the temperature and deformation of key characteristic points inside the tank; step 7, based on the real-time feedback of the temperature and deformation of key characteristic points inside the tank, the friction stir welding process parameters are controlled in real time to ensure that the temperature of key characteristic points remains basically unchanged, thereby realizing the constant temperature and constant deformation control of the friction stir welding of the large-diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom ring seam.

[0005] In the 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom annular seam assembly welding method based on constant temperature control provided by the present invention, it can also have the following characteristics: wherein, in step 1, the barrel section and the double-layer common bottom structure are respectively a three-stage tank barrel section and an aluminum-lithium alloy PMI interlayer common bottom structure.

[0006] In the 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom annular seam assembly welding method based on constant temperature control provided by the present invention, it can also have the following characteristics: wherein, the specific process of establishing the data set in step 4 is: based on the barrel section-double-layer common bottom structure lock bottom annular seam stir friction welding finite element simulation model, through high-throughput calculation, the tank surface temperature field under different welding conditions, the temperature and deformation of the key characteristic points inside the tank are established, and the tank surface temperature field is further discretized into a temperature field matrix data set.

[0007] In the 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom ring seam assembly welding method based on constant temperature control provided by the present invention, it can also have the following characteristics: wherein, the specific process of establishing the deep learning model in step 5 is: taking the tank surface temperature field as input, and taking the temperature and deformation of the key characteristic points inside the tank as output, a deep learning model of the temperature / deformation of the key characteristic points inside the tank-tank surface temperature field is established.

[0008] In the 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom annular seam assembly welding method based on constant temperature control provided by the present invention, it can also have the following characteristics: wherein, in step 5, the temperature / deformation of the key characteristic points inside the tank-the temperature field of the tank surface deep learning model includes a three-layer convolutional neural network and a fully connected neural network. The convolutional neural network gradually extracts the temperature field feature information through multiple convolution-pooling-expansion operations, and further processes the temperature field feature information through the flattening layer into a high-dimensional vector and inputs it into the fully connected neural network. Finally, the temperature field feature information vector is fitted with the temperature and deformation of the key characteristic points inside the tank through the fully connected neural network, so as to achieve accurate prediction of the temperature and deformation of the key characteristic points inside the tank.

[0009] In the 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom annular seam assembly welding method based on constant temperature control provided by the present invention, it can also have the following characteristics: wherein, in step 6, an infrared thermal imager is used to measure the real-time temperature of the tank surface to obtain the real-time temperature of key observation points on the tank surface.

[0010] In the 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom annular seam assembly welding method based on constant temperature control provided by the present invention, it can also have the following characteristics: wherein, in step 7, the stir friction welding process parameters include at least the stirring head downward pressure, welding speed and rotation speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a schematic diagram of a 5m diameter aluminum-lithium alloy PMI sandwich common bottom lock bottom annular seam assembly welding method based on constant temperature control in an embodiment of the present invention;

[0012] Figure 2 It is a finite element simulation model diagram of the friction stir welding of the bottom-locking annular seam of the barrel section-double-layer common bottom structure based on the mobile heat source and mobile load method in the embodiment of the present invention;

[0013] Figure 3 This is a diagram showing the temperature distribution results of the friction stir welding of the bottom-locking annular seam of the barrel section-double-layer common bottom structure in an embodiment of the present invention;

[0014] Figure 4 This is a diagram showing the deformation results of the key characteristic points inside the friction stir welding of the bottom locking annular seam of the barrel section-double-layer common bottom structure in the embodiment of the present invention;

[0015] Figure 5 It is a deep learning model diagram of the temperature / deformation-surface temperature field of key points inside the tank in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0017] The present embodiment provides a 5m diameter aluminum-lithium alloy PMI sandwich common bottom lock bottom annular seam assembly welding method based on constant temperature control, which realizes the high-efficiency assembly and high-quality stir friction welding of the barrel section and the double-layer common bottom structure lock bottom annular seam.

[0018] Figure 1 It is a schematic diagram of a 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom annular seam assembly welding method based on constant temperature control in an embodiment of the present invention.

[0019] like Figure 1 As shown, the 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom annular seam assembly welding method based on constant temperature control involved in this embodiment includes the following steps:

[0020] Step S1, taking the three-stage tank barrel section and the aluminum-lithium alloy PMI sandwich common bottom as the object, before the barrel section and the double-layer common bottom structure are sheathed, the butt end of the barrel section is locally heated by an induction heating method to expand the butt end of the barrel section, and then the sheathing of the barrel section and the double-layer common bottom structure is completed.

[0021] Step S2, after the assembly is completed, wait for the butt end of the barrel section to cool and shrink, so as to achieve interference fit assembly between the barrel section and the bottom locking ring seam of the double-layer common bottom structure.

[0022] Step S3, according to the working conditions of the friction stir welding of the bottom locking annular seam of the barrel section and the double-layer common bottom structure, a finite element simulation model of the friction stir welding of the bottom locking annular seam of the barrel section and the double-layer common bottom structure is established by using the moving heat source and moving load method.

[0023] Figure 2 It is a finite element simulation model diagram of the friction stir welding of the locked bottom annular seam of the barrel section-double-layer common bottom structure based on the mobile heat source and mobile load method in an embodiment of the present invention.

[0024] Step S4, based on the above-established finite element simulation model of the bottom-locking annular seam friction stir welding of the barrel section-double-layer common bottom structure, through high-throughput calculation, a data set of the tank surface temperature field, the temperature and deformation of key characteristic points inside the tank under different welding conditions is established, and the tank surface temperature field is further discretized into a temperature field matrix data set.

[0025] In this embodiment, the temperature of the key characteristic points inside the tank includes the extreme temperature of the inner core area of ​​the friction stir welding.

[0026] Figure 3 This is a diagram showing the temperature distribution results of the friction stir welding of the bottom-locking annular seam of the barrel section-double-layer common bottom structure in an embodiment of the present invention.

[0027] Step S5, based on the established data set, taking the tank surface temperature field as input and the temperature and deformation of the key characteristic points inside the tank as output, establish a deep learning model of the temperature / deformation of the key characteristic points inside the tank - the tank surface temperature field.

[0028] The deep learning model in this embodiment includes a three-layer convolutional neural network (CNN) and a fully connected neural network (FCNN). The convolutional neural network gradually extracts temperature field feature information through multiple convolution-pooling-expansion operations, and further processes the temperature field feature information into a high-dimensional vector through a flattening layer and inputs it into the FCNN. Finally, the temperature field feature information vector is fitted with the temperature and deformation of the key feature points inside the tank through the FCNN to achieve accurate prediction of the temperature and deformation of the key feature points inside the tank.

[0029] Figure 4 This is a diagram showing the deformation results of the key characteristic points inside the friction stir welding of the locked bottom annular seam of the barrel section-double-layer common bottom structure in an embodiment of the present invention.

[0030] Figure 5 It is a deep learning model diagram of the temperature / deformation-surface temperature field of key points inside the tank in an embodiment of the present invention.

[0031] Step S6: During the friction stir welding process of the cylinder section and the double-layer common bottom structure lock bottom annular seam, an infrared thermal imager is used to measure the real-time temperature of the tank surface. The temperature of key observation points on the tank surface is read and input into the established deep learning model, so as to realize real-time feedback of the temperature and deformation of key characteristic points inside the tank during the friction stir welding process based on the tank surface temperature field measurement data.

[0032] Step S7, based on the real-time feedback of the temperature and deformation of the key characteristic points inside the tank, the stir friction welding process parameters such as the downward pressure of the stirring head, the welding speed, the rotation speed, etc. are controlled in real time to ensure that the temperature of the key characteristic points remains basically unchanged, thereby achieving constant temperature and constant deformation control of the stir friction welding of the common bottom lock ring seam of the large diameter aluminum-lithium alloy PMI interlayer.

[0033] Compared with the prior art, the 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom ring seam assembly welding method based on constant temperature control provided in this embodiment first locally heats the butt end of the barrel section by an induction heating method, and utilizes the thermal expansion of the barrel section end to achieve interference fit with the double-layer common bottom structure lock bottom ring seam, which can avoid large deformation in the local area of ​​the end and cause stress concentration; then, a barrel section-double-layer common bottom structure lock bottom ring seam stir friction welding finite element simulation model based on a mobile heat source and mobile load method and a tank internal key characteristic point temperature / deformation-tank surface temperature field deep learning model are established, and the temperature and deformation of the key characteristic points inside the tank during the stir friction welding process are fed back in real time according to the tank surface temperature field measurement data, so that the welding heat input can be controlled in real time by adjusting the stir friction welding parameters, and the welding deformation of the large diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom ring seam can be reduced.

[0034] The above-mentioned embodiments are preferred examples of the present invention and are not intended to limit the protection scope of the present invention.

Claims

1. A 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom annular seam assembly welding method based on constant temperature control, characterized in that: The following steps are involved: Step 1, before the barrel section and the double-layer common bottom structure are fitted together, the butt joint end of the barrel section is locally heated by an induction heating method to expand the butt joint end of the barrel section, thereby completing the fitting of the barrel section and the bottom locking annular seam of the double-layer common bottom structure; Step 2, after the assembly is completed, waiting for the butt joint end of the barrel section to cool and shrink, so as to achieve interference fit assembly of the barrel section and the bottom locking ring seam of the double-layer common bottom structure; Step 3, using the mobile heat source and mobile load method to establish a finite element simulation model of the friction stir welding of the bottom-locked annular seam of the barrel section-double-layer common bottom structure; Step 4, establishing a data set through high-throughput calculation according to the finite element simulation model of the bottom-locking annular seam stir welding of the barrel section-double-layer common bottom structure; Step 5: Based on the data set, establish a deep learning model of the temperature / deformation of key characteristic points inside the tank and the temperature field of the tank surface; Step 6, during the friction stir welding process of the cylinder section and the double-layer common bottom structure lock bottom annular seam, the real-time temperature of the key observation points on the tank surface is input into the deep learning model of the key characteristic point temperature / deformation inside the tank-tank surface temperature field, so as to provide real-time feedback on the temperature and deformation of the key characteristic points inside the tank; Step 7, based on the real-time feedback of the temperature and deformation of the key characteristic points inside the tank, the stir friction welding process parameters are controlled in real time to ensure that the temperature of the key characteristic points remains basically unchanged, thereby achieving constant temperature and constant deformation control of the stir friction welding of the large-diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom annular seam.

2. The 5m diameter aluminum-lithium alloy PMI sandwich common bottom lock bottom annular seam assembly welding method based on constant temperature control according to claim 1 is characterized in that: in, In step 1, the barrel section and the double-layer common bottom structure are respectively a three-stage tank barrel section and an aluminum-lithium alloy PMI sandwich common bottom structure.

3. The 5m diameter aluminum-lithium alloy PMI sandwich common bottom lock bottom annular seam assembly welding method based on constant temperature control according to claim 1 is characterized in that: in, The specific process of establishing the data set in step 4 is: According to the finite element simulation model of the friction stir welding of the locked bottom annular seam of the barrel section-double-layer common bottom structure, through high-throughput calculation, a data set of the tank surface temperature field, the temperature and deformation of the key characteristic points inside the tank under different welding conditions is established, and the tank surface temperature field is further discretized into a temperature field matrix data set.

4. The 5m diameter aluminum-lithium alloy PMI interlayer common bottom lock bottom annular seam assembly welding method based on constant temperature control according to claim 1 is characterized in that: in, The specific process of establishing a deep learning model in step 5 is: Taking the tank surface temperature field as input and the temperature and deformation of key characteristic points inside the tank as output, a deep learning model of the temperature / deformation of key characteristic points inside the tank and the tank surface temperature field is established.

5. The 5m diameter aluminum-lithium alloy PMI sandwich common bottom lock bottom annular seam assembly welding method based on constant temperature control according to claim 1 is characterized in that: in, In step 5, the deep learning model of the temperature / deformation of the key characteristic points inside the tank and the temperature field of the tank surface includes a three-layer convolutional neural network and a fully connected neural network. The convolutional neural network gradually extracts temperature field feature information through multiple convolution-pooling-expansion operations, and further processes the temperature field feature information into a high-dimensional vector through a flattening layer and inputs it into the fully connected neural network. Finally, the temperature field feature information vector is fitted with the temperature and deformation of key feature points inside the tank through the fully connected neural network to achieve accurate prediction of the temperature and deformation of key feature points inside the tank.

6. The 5m diameter aluminum-lithium alloy PMI sandwich common bottom lock bottom annular seam assembly welding method based on constant temperature control according to claim 1 is characterized in that: in, In step 6, an infrared thermal imager is used to measure the real-time temperature of the tank surface, thereby obtaining the real-time temperature of key observation points on the tank surface.

7. The 5m diameter aluminum-lithium alloy PMI sandwich common bottom lock bottom annular seam assembly welding method based on constant temperature control according to claim 1 is characterized in that: in, In step 7, the friction stir welding process parameters include at least the amount of pressure applied by the stirring head, the welding speed and the rotation speed.

Images