Design and manufacturing method of dock folded structural member based on artificial intelligence and machine vision

Abstract

The invention discloses an artificial intelligence and machine vision-based design and manufacturing method and system for a dock folded structural member, computer equipment and a readable storage medium. Comprising the following steps: constructing an initial 3D printing model of the dock folding structural member; in the 3D forming printing process, an infrared thermal imaging method is adopted to detect printing defects in real time, a convolutional neural network is utilized to extract image features of real-time infrared thermal imaging, the extracted image features are detected and recognized to obtain different defect types, initial printing parameters are adjusted according to a feedback result, and target printing parameters are obtained; carrying out X-ray nondestructive testing on the dock collapsed structural member, and obtaining internal structure defect parameters; and according to the internal structure defect parameters, the size correction amount is obtained, and target structure parameters and a target 3D printing model are obtained. By adopting artificial intelligence and machine vision methods, defects can be efficiently and accurately found and recognized, printing parameters are corrected, a target model is updated, and the product size and performance precision are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer-aided simulation design and additive manufacturing technology, and in particular to a design and manufacturing method, system, computer equipment, and computer-readable storage medium for dock folding structural parts based on artificial intelligence and machine vision. Background Art

[0002] With the development of additive manufacturing technology, its application field is becoming more and more extensive, and computer-aided simulation design and manufacturing have also penetrated into the design and manufacturing process of various structures. As an important equipment for marine and ship engineering, dock folding structural parts play a vital role in the design and manufacturing process of ships. However, in the prior art, empirical design is generally used to determine the dimensional parameters, and then verified by experimental means. In this regard, on the one hand, the well-designed structural model used in the prior art may not be directly capable of additive manufacturing and processing. First, for thin-walled, long-suspended rod bases and surface base lattices, large deformation, collapse, rupture and other failures occur during printing due to thermal stress and powder support strength; second, the memory of some lattices is too large, and the software processing capacity is limited during slicing, and the pre-processing such as support setting and slicing cannot be completed within a reasonable time. In addition, the design means in the prior art are limited, the efficiency is low, the error is large, the product precision is poor, and there are many defects, which seriously affect the high-quality development of ship and ocean engineering. Summary of the invention

[0003] In view of the above defects or improvement needs of the prior art, the present invention provides a method, system, computer device, and computer-readable storage medium for designing and manufacturing dock folding structural parts based on artificial intelligence and machine vision. The method of artificial intelligence and machine vision can efficiently and accurately find and identify defects, correct printing parameters, and update the target model to improve product size and performance accuracy.

[0004] To achieve the above purpose, the present invention adopts the following technical solution.

[0005] In some embodiments, a method for designing and manufacturing a dock folding structure based on artificial intelligence and machine vision is provided, the method comprising:

[0006] Constructing an initial 3D printing model of the dock folding structure, wherein the initial 3D printing model includes initial structural parameters, and the initial structural parameters include at least the number of pores and the size of the pores;

[0007] Performing 3D molding printing according to the initial 3D printing model, wherein the 3D molding printing includes initial printing parameters;

[0008] During the 3D molding printing process, an infrared thermal imaging method is used to detect printing defects in real time, and the initial printing parameters are adjusted according to the feedback results to obtain target printing parameters;

[0009] Perform 3D molding printing according to the target printing parameters;

[0010] After the 3D molding printing is completed according to the target printing parameters, the dock folded structure is subjected to X-ray nondestructive testing to obtain internal structural defect parameters;

[0011] Obtaining a size correction amount according to the internal structural defect parameter;

[0012] According to the size correction amount, the initial structural parameters are corrected to obtain target structural parameters and a target 3D printing model, wherein the target 3D printing model includes the target structural parameters;

[0013] Perform 3D printing according to the target 3D printing model and target printing parameters to obtain a dock folding structure;

[0014] Among them, an infrared thermal imaging method is used to perform real-time detection of printing defects, including: using a convolutional neural network to extract image features of real-time infrared thermal imaging, detecting the extracted image features, and identifying different defect types.

[0015] In some embodiments, the real-time detection of printing defects using infrared thermal imaging methods also includes: extracting image features of the infrared thermal imaging corresponding to the defect based on the defect position, and using wavelet transform to extract time series signals of different defects, and analyzing the differences in time series signals of different defects, so as to more accurately identify different defect types.

[0016] In some embodiments, performing X-ray nondestructive testing on the dock's folded structure and obtaining internal structural defect parameters includes: performing X-ray nondestructive testing on the dock's folded structure, acquiring X-ray images, and using computer vision image processing methods to obtain size parameters of pore defects.

[0017] In some embodiments, constructing the initial 3D printing model of the dock folding structure includes: performing shrinkage processing on connection holes with assembly accuracy requirements; and performing wall thickening processing on surfaces with assembly accuracy requirements.

[0018] In some embodiments, the wall thickening process includes increasing the wall thickness of the connecting hole by 2-4 mm.

[0019] In some embodiments, constructing the initial 3D printing model of the dock folding structure also includes: designing machining datums in at least two orthogonal directions on the outer surface of the model, wherein the machining datums are used for machining of assembly dimensions and can be removed by CNC machining after 3D printing.

[0020] In some embodiments, the method further comprises: after obtaining the dock folding structure by 3D printing, performing post-processing to obtain a qualified dock folding structure;

[0021] Among them, post-processing at least includes powder bed cleaning, substrate separation, heat treatment, support cleaning, processing and assembly size, internal flow channel surface treatment, surface sandblasting, size and surface defect detection.

[0022] In some embodiments, a dock folding structure design and manufacturing system based on artificial intelligence and machine vision is also provided, characterized in that the system includes:

[0023] An initial 3D printing model construction module is used to construct an initial 3D printing model of the dock folding structure, wherein the initial 3D printing model includes initial structural parameters, and the initial structural parameters include at least the number of pores and the size of the pores;

[0024] A 3D molding and printing module, used for performing 3D molding and printing according to the initial 3D printing model, wherein the 3D molding and printing includes initial printing parameters;

[0025] An artificial intelligence and machine vision module, used to detect printing defects in real time using an infrared thermal imaging method during the 3D molding printing process, and to adjust the initial printing parameters according to the feedback results to obtain target printing parameters;

[0026] The 3D molding printing module is further used to perform 3D molding printing according to the target printing parameters;

[0027] An X-ray nondestructive testing and computer vision module is used to perform X-ray nondestructive testing on the dock folded structure after the 3D molding printing is completed according to the target printing parameters, and obtain internal structural defect parameters;

[0028] A size correction module, used to obtain a size correction amount according to the internal structure defect parameter;

[0029] The size correction module is further used to correct the initial structural parameters according to the size correction amount to obtain target structural parameters and a target 3D printing model, wherein the target 3D printing model includes the target structural parameters;

[0030] The 3D molding and printing module is further used to perform 3D printing according to the target 3D printing model and target printing parameters to obtain the dock folding structure;

[0031] Among them, an infrared thermal imaging method is used to perform real-time detection of printing defects, including: using a convolutional neural network to extract image features of real-time infrared thermal imaging, detecting the extracted image features, and identifying different defect types.

[0032] In some embodiments, the real-time detection of printing defects using infrared thermal imaging methods also includes: extracting image features of the infrared thermal imaging corresponding to the defect based on the defect position, and using wavelet transform to extract time series signals of different defects, and analyzing the differences in time series signals of different defects, so as to more accurately identify different defect types.

[0033] In some embodiments, performing X-ray nondestructive testing on the dock's folded structure and obtaining internal structural defect parameters includes: performing X-ray nondestructive testing on the dock's folded structure, acquiring X-ray images, and using computer vision image processing methods to obtain size parameters of pore defects.

[0034] In some embodiments, an electronic device is also provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described methods when executing the program.

[0035] In some embodiments, a computer-readable storage medium is further provided, characterized in that the storage medium stores a computer program, and when the computer program is executed by a processor, any of the methods described above is implemented.

[0036] Compared with the prior art, the beneficial effects of the present invention are:

[0037] In some embodiments of the present application, based on artificial intelligence and machine vision, an infrared thermal imaging method is used to detect printing defects in real time, and a convolutional neural network is used to extract image features of real-time infrared thermal imaging, and the extracted image features are detected to identify different types of defects. The present application performs defect recognition in the 3D printing process, and can efficiently and accurately find and identify defects and make printing parameter corrections. In addition, through X-ray nondestructive testing, internal structural defect parameters are obtained to update the target model and improve product size and performance accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The present invention is a flowchart of a method for designing and manufacturing a dock folding structure based on artificial intelligence and machine vision according to an embodiment of the present invention.

[0039] Figure 2 This is a schematic diagram of real-time defect detection based on the combination of infrared thermal imaging and machine vision according to an embodiment of the present invention.

[0040] Figure 3 A schematic diagram of metal part printing quality assessment based on X-ray and computer vision according to an embodiment of the present invention.

[0041] Figure 4Schematic diagram of a metal 3D printing process window according to an embodiment of the present invention.

[0042] Figure 5 The present invention is a schematic diagram of the process flow of post-processing of a dock folded structure according to an embodiment of the present invention.

[0043] Figure 6 This is a schematic diagram of a dock folding structure design and manufacturing system based on artificial intelligence and machine vision according to an embodiment of the present invention.

[0044] Figure 7 A schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0046] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0047] In the process of additive manufacturing using 3D printing, the designed 3D model may not be able to be processed. The main reasons are: first, for thin-walled, long-suspended rod-based and surface-based lattices, large deformation, collapse, cracking and other failures occur during printing due to thermal stress and powder support strength; second, the memory of some lattices is too large, and the software processing capacity is limited during slicing, and it is impossible to complete the support setting, slicing and other pre-processing within a reasonable time. For samples with extremely small curved surface lattices, the error between the actual printed size and the designed model size is compared. The maximum Z-direction error is 0.368mm. For parts with thinner wall thickness and larger suspended surfaces, the size error is larger. The reason for the error is that the measurement point is located on the suspended surface, which is supported by the powder below during printing. The powder softening strength is not enough, resulting in slight collapse.

[0048] In this regard, in some embodiments, dimensional corrections can be made based on experience. Specifically, the feasibility of printing each part of the structure is analyzed based on experience and trial printing. For example, in order to prevent the cavity from deforming and collapsing, the horizontal inner cavity with a larger diameter is changed into a teardrop-shaped contour. The bottom surface of the boss with a height of more than 0.6 mm on the vertical surface is set to an inclined surface with an inclination angle greater than 45 degrees. These methods can achieve accurate molding of local important dimensions.

[0049] In some embodiments, in addition to adjusting the size, for some features with high conformal requirements, the molding accuracy can be improved by adding removable supports and auxiliary connecting blocks. The supports can be removed smoothly after printing by machining or manual methods. The auxiliary connecting blocks are used to improve the shape accuracy. For "free growth" surfaces with high precision but no mutual constraints during printing, auxiliary connecting blocks that can be easily removed by machining can be added between the two thin plate planes. The auxiliary connecting blocks play a role in ensuring the parallelism between the two thin plates.

[0050] In the above embodiments, the size modification and the addition of auxiliary blocks are generally completed based on manual experience. In some embodiments of the present application, a design and manufacturing method of a dock folding structure based on artificial intelligence and machine vision is also provided, which can adjust the configuration size through multimodal learning and machine vision methods.

[0051] Figure 1 The figure is a schematic diagram of the overall process of a method for designing and manufacturing a dock folding structure based on artificial intelligence and machine vision according to an embodiment of the present invention. Figure 1 In some embodiments of the present application, a method for designing and manufacturing a dock folding structure based on artificial intelligence and machine vision is also provided, the method comprising:

[0052] Constructing an initial 3D printing model of the dock folding structure, wherein the initial 3D printing model includes initial structural parameters, and the initial structural parameters include at least the number of pores and the size of the pores;

[0053] Performing 3D molding printing according to the initial 3D printing model, wherein the 3D molding printing includes initial printing parameters;

[0054] During the 3D molding printing process, an infrared thermal imaging method is used to detect printing defects in real time, and the initial printing parameters are adjusted according to the feedback results to obtain target printing parameters;

[0055] Perform 3D molding printing according to the target printing parameters;

[0056] After the 3D molding printing is completed according to the target printing parameters, the dock folded structure is subjected to X-ray nondestructive testing to obtain internal structural defect parameters;

[0057] Obtaining a size correction amount according to the internal structural defect parameter;

[0058] According to the size correction amount, the initial structural parameters are corrected to obtain target structural parameters and a target 3D printing model, wherein the target 3D printing model includes the target structural parameters;

[0059] Perform 3D printing according to the target 3D printing model and target printing parameters to obtain a dock folding structure;

[0060] Among them, an infrared thermal imaging method is used to perform real-time detection of printing defects, including: using a convolutional neural network to extract image features of real-time infrared thermal imaging, detecting the extracted image features, and identifying different defect types.

[0061] In the embodiments of the present application, the dock folding structure can be a fixed structure of the dock support body, as well as a precision valve body and hydraulic components. The combination of laser process parameters in additive manufacturing largely determines the geometric shape, local structure, defect size and defect morphology of the molten pool. Therefore, the online monitoring technology of additive manufacturing is of great significance to the size, performance evaluation and practical application of additive manufacturing products. As the current mainstream monitoring technology, non-destructive testing technology has expanded from infrared thermal imaging detection, penetrant detection and eddy current method to ultrasonic detection and X-ray detection. Infrared thermal imaging is sensitive to the surface and internal heat transfer of the molten pool. It has the advantages of being fast, non-contact and can be used for large-area detection, but it cannot provide information such as the vertical morphology and microstructure characteristics of the molten pool. X-ray imaging technology uses X-rays to penetrate objects and detect internal defects by analyzing transmission images. It is particularly suitable for metal prints. It can provide high-resolution internal structure images and detect tiny pores.

[0062] In the molding process printing of the embodiment of the present application, a convolutional neural network is used to extract real-time infrared thermal imaging features, the extracted features are used to detect and identify different defect types, the defect type and defect quantity are fed back to the machine, and the control system adjusts the printing operation and corresponding printing parameters according to the feedback results.

[0063] Figure 2 This is a schematic diagram of real-time defect detection based on the combination of infrared thermal imaging and machine vision according to an embodiment of the present invention. Figure 2In some embodiments, the use of infrared thermal imaging to detect printing defects in real time also includes: extracting image features of infrared thermal imaging corresponding to the defect according to the defect position, extracting time series signals of different defects using wavelet transform, and analyzing the differences in time series signals of different defects, so as to more accurately identify different defect types. In the embodiment of the present application, the infrared image of the corresponding defect is extracted according to the defect position, and the time series signals of different defects are extracted using wavelet transform, and the differences in the sequence signals of different defects are further analyzed and determined, so as to more accurately identify different defect types.

[0064] Figure 3 Schematic diagram of metal part printing quality assessment based on X-ray and computer vision according to an embodiment of the present invention. Figure 3 In some embodiments, the performing of X-ray nondestructive testing on the dock folded structure and obtaining internal structural defect parameters includes: performing X-ray nondestructive testing on the dock folded structure, obtaining X-ray images, and obtaining size parameters of pore defects using computer vision image processing methods. In the embodiment of the present application, after the molding process is printed, X-ray nondestructive testing is performed on the molded metal parts to obtain X-ray images, and the size parameters related to the pore defects of the metal parts are obtained using computer vision image processing methods, and the printing quality of the molded metal parts is evaluated at the same time according to information such as the number and size of pores.

[0065] Figure 4 This is a schematic diagram of a metal 3D printing process window according to an embodiment of the present invention. Figure 4 By using the above-mentioned real-time defect detection of infrared images during printing and using X-rays to evaluate the defect of printed parts after printing to evaluate the printing quality, the printing process window of the structural parts and the correction amount of the initial size of the structural parts can be given to improve the product size and performance accuracy.

[0066] In some embodiments, constructing the initial 3D printing model of the dock folding structure includes: performing shrinkage processing on connection holes with assembly accuracy requirements; and performing wall thickening processing on surfaces with assembly accuracy requirements.

[0067] The metal additive manufacturing process is essentially a special casting, which is a process of rapid melting and solidification of powder under the irradiation of a high-energy laser beam. Therefore, it has larger size and shape errors than compression molding and CNC machining. For the connection dimensions such as holes and grooves on the dock folding structure that need to be assembled with other components, it is necessary to ensure the accuracy through CNC machining after printing. The surface of the dock folding structure is a continuous shell. Printing errors will cause the wall thickness to be thinned during CNC machining of the connection part, thereby reducing the connection strength. During CNC machining, the dock folding structure has many special-shaped features and there is no ready-made machining benchmark. In some embodiments, the benchmark needs to be machined first, which introduces machining errors and reduces the shell thickness in the benchmark area.

[0068] For the connection holes and surfaces with assembly accuracy requirements, shrinkage and wall thickness thickening treatments are performed after the model design is completed. Shrinkage is to reduce the diameter of the original larger hole (minimum diameter 1mm). In some embodiments, the wall thickness thickening treatment includes increasing the wall thickness of the connection hole wall by 2-4mm. In the embodiment of the present application, the wall thickness of the connection hole wall is increased by 2-4mm. If the wall thickness is less than 2mm, the large-size printing error will affect the wall thickness. If the thickening is greater than 4mm, it will affect the lightweight effect of the structure and change the local stiffness of the structure. In some embodiments, constructing the initial 3D printing model of the dock folding structure also includes: designing machining datums in at least two orthogonal directions on the outer surface of the model, and the machining datums are used for machining of assembly dimensions and surfaces, and can be removed by CNC machining after 3D printing.

[0069] Machining datums have a direct impact on the machining accuracy of the assembly dimensions of 3D printed special-shaped structural parts. In the embodiment of the present application, machining datums in at least two orthogonal directions are designed in advance on the outer surface of the model. The design of machining datums follows the principles of orthogonality, removability, and proximity to important machining dimensions. After the important assembly dimensions are machined, the machining datums can be removed by CNC machining.

[0070] Figure 5 The figure is a schematic diagram of the process flow of the post-processing link of the dock folded structure according to one embodiment of the present invention. Figure 5 In some embodiments, the method further comprises: after obtaining the dock folding structure by 3D printing, performing post-processing to obtain a qualified dock folding structure;

[0071] Among them, post-processing at least includes powder bed cleaning, substrate separation, heat treatment, support cleaning, processing and assembly size, internal flow channel surface treatment, surface sandblasting, size and surface defect detection.

[0072] Specifically, the dock folding structure needs to be post-processed after printing. The post-processing steps include:

[0073] Remove the powder from the powder bed covering the printed part;

[0074] The workpiece and the 3D printed substrate are separated by wire cutting, and the residual powder inside is removed through the powder cleaning hole with the assistance of high pressure source;

[0075] A heat treatment procedure will be formulated, and the workpiece will be sent to a large-volume heat treatment furnace for heat treatment according to the procedure;

[0076] Perform preliminary grinding by manually removing support residues on the surface and inside the channel;

[0077] Process the required assembly dimensions by machining methods;

[0078] The surface roughness of the internal flow channel was reduced by abrasive flow grinding and local electrolytic polishing;

[0079] Perform surface sandblasting to further reduce surface roughness;

[0080] Through measurement and non-destructive testing methods, the dimensional accuracy and surface crack defects are inspected to confirm that the product is qualified.

[0081] Through the post-processing steps above, the microstructure regulation of the workpiece, the elimination of thermal stress, and the accurate control of assembly dimensions and surface roughness can be completed, thus achieving qualified delivery of products from size to performance.

[0082] Figure 6 This is a schematic diagram of a dock folding structure design and manufacturing system based on artificial intelligence and machine vision according to an embodiment of the present invention. Figure 6 In some embodiments of the present application, a dock folding structure design and manufacturing system based on artificial intelligence and machine vision is also provided, and the system includes:

[0083] An initial 3D printing model construction module is used to construct an initial 3D printing model of the dock folding structure, wherein the initial 3D printing model includes initial structural parameters, and the initial structural parameters include at least the number of pores and the size of the pores;

[0084] A 3D molding and printing module, used for performing 3D molding and printing according to the initial 3D printing model, wherein the 3D molding and printing includes initial printing parameters;

[0085] An artificial intelligence and machine vision module, used to detect printing defects in real time using an infrared thermal imaging method during the 3D molding printing process, and to adjust the initial printing parameters according to the feedback results to obtain target printing parameters;

[0086] The 3D molding printing module is further used to perform 3D molding printing according to the target printing parameters;

[0087] An X-ray nondestructive testing and computer vision module is used to perform X-ray nondestructive testing on the dock folded structure after the 3D molding printing is completed according to the target printing parameters, and obtain internal structural defect parameters;

[0088] A size correction module, used to obtain a size correction amount according to the internal structure defect parameter;

[0089] The size correction module is further used to correct the initial structural parameters according to the size correction amount to obtain target structural parameters and a target 3D printing model, wherein the target 3D printing model includes the target structural parameters;

[0090] The 3D molding and printing module is further used to perform 3D printing according to the target 3D printing model and target printing parameters to obtain the dock folding structure;

[0091] Among them, an infrared thermal imaging method is used to perform real-time detection of printing defects, including: using a convolutional neural network to extract image features of real-time infrared thermal imaging, detecting the extracted image features, and identifying different defect types.

[0092] In some embodiments, the real-time detection of printing defects using infrared thermal imaging methods also includes: extracting image features of the infrared thermal imaging corresponding to the defect based on the defect position, and using wavelet transform to extract time series signals of different defects, and analyzing the differences in time series signals of different defects, so as to more accurately identify different defect types.

[0093] In some embodiments, performing X-ray nondestructive testing on the dock's folded structure and obtaining internal structural defect parameters includes: performing X-ray nondestructive testing on the dock's folded structure, acquiring X-ray images, and using computer vision image processing methods to obtain size parameters of pore defects.

[0094] refer to Figure 7 In some embodiments, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the numerical simulation, analysis, or control steps in any of the above methods are implemented.

[0095] At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1The alloy structure optimization design and manufacturing method described above. Of course, in addition to the software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices. It can be understood that it is only necessary to program the method flow slightly in a hardware description language and program it into an integrated circuit to obtain a hardware circuit that implements the logical method flow.

[0096] The above method can be implemented by a controller in any appropriate manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include but are not limited to microcontrollers. The memory controller can also be implemented as part of the control logic of the memory. It is understandable that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0097] The systems, devices, modules or units in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0098] For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing this specification, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0099] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, this specification may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0100] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] In some embodiments, a computer-readable storage medium is further provided, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, any of the above-described methods is implemented.

[0102] In some embodiments, these computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0103] In some embodiments, these computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0104] In some embodiments, the computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0105] In some embodiments, the memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0106] In some embodiments, computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0107] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for designing and manufacturing dock folding structural parts based on artificial intelligence and machine vision, characterized in that: The method comprises: Constructing an initial 3D printing model of the dock folding structure, wherein the initial 3D printing model includes initial structural parameters, and the initial structural parameters include at least the number of pores and the size of the pores; Performing 3D molding printing according to the initial 3D printing model, wherein the 3D molding printing includes initial printing parameters; During the 3D molding printing process, an infrared thermal imaging method is used to detect printing defects in real time, and the initial printing parameters are adjusted according to the feedback results to obtain target printing parameters; Perform 3D molding printing according to the target printing parameters; After the 3D molding printing is completed according to the target printing parameters, the dock folded structure is subjected to X-ray nondestructive testing to obtain internal structural defect parameters; Obtaining a size correction amount according to the internal structural defect parameter; According to the size correction amount, the initial structural parameters are corrected to obtain target structural parameters and a target 3D printing model, wherein the target 3D printing model includes the target structural parameters; Perform 3D printing according to the target 3D printing model and target printing parameters to obtain a dock folding structure; Among them, an infrared thermal imaging method is used to perform real-time detection of printing defects, including: using a convolutional neural network to extract image features of real-time infrared thermal imaging, detecting the extracted image features, and identifying different defect types.

2. The method for designing and manufacturing a dock folding structure according to claim 1, characterized in that: The real-time detection of printing defects using infrared thermal imaging method also includes: extracting image features of infrared thermal imaging corresponding to the defect according to the defect position, extracting time series signals of different defects using wavelet transform, and analyzing the differences in time series signals of different defects, so as to more accurately identify different defect types.

3. The method for designing and manufacturing a dock folding structure according to claim 1, characterized in that: The method of performing X-ray nondestructive testing on the dock folded structure and obtaining internal structure defect parameters includes: performing X-ray nondestructive testing on the dock folded structure, obtaining X-ray images, and obtaining size parameters of pore defects using computer vision image processing methods.

4. The method for designing and manufacturing a dock folding structure according to claim 1, characterized in that: Constructing the initial 3D printing model of the dock folding structure includes: performing shrinkage processing on the connection holes with assembly accuracy requirements; and performing wall thickness thickening processing on the surfaces with assembly accuracy requirements.

5. The method for designing and manufacturing a dock folding structure according to claim 4, characterized in that: The wall thickness increasing process includes increasing the wall thickness of the connecting hole by 2-4 mm.

6. The method for designing and manufacturing a dock folding structure according to claim 5, characterized in that: Constructing the initial 3D printing model of the dock folding structure also includes: designing at least two machining datums in orthogonal directions on the outer surface of the model, the machining datums are used for machining of assembly dimensions, and can be removed by CNC machining after 3D printing.

7. The method for designing and manufacturing a dock folding structure according to claim 6, characterized in that: The method further comprises: after obtaining the dock folding structure by 3D printing, performing post-processing to obtain a qualified dock folding structure; Among them, post-processing at least includes powder bed cleaning, substrate separation, heat treatment, support cleaning, processing and assembly size, internal flow channel surface treatment, surface sandblasting, size and surface defect detection.

8. A dock folding structure design and manufacturing system based on artificial intelligence and machine vision, characterized in that: The system comprises: An initial 3D printing model construction module is used to construct an initial 3D printing model of the dock folding structure, wherein the initial 3D printing model includes initial structural parameters, and the initial structural parameters include at least the number of pores and the size of the pores; A 3D molding and printing module, used for performing 3D molding and printing according to the initial 3D printing model, wherein the 3D molding and printing includes initial printing parameters; An artificial intelligence and machine vision module, used to detect printing defects in real time using an infrared thermal imaging method during the 3D molding printing process, and to adjust the initial printing parameters according to the feedback results to obtain target printing parameters; The 3D molding printing module is further used to perform 3D molding printing according to the target printing parameters; An X-ray nondestructive testing and computer vision module is used to perform X-ray nondestructive testing on the dock folded structure after the 3D molding printing is completed according to the target printing parameters, and obtain internal structural defect parameters; A size correction module, used to obtain a size correction amount according to the internal structure defect parameter; The size correction module is further used to correct the initial structural parameters according to the size correction amount to obtain target structural parameters and a target 3D printing model, wherein the target 3D printing model includes the target structural parameters; The 3D molding and printing module is further used to perform 3D printing according to the target 3D printing model and target printing parameters to obtain the dock folding structure; Among them, an infrared thermal imaging method is used to perform real-time detection of printing defects, including: using a convolutional neural network to extract image features of real-time infrared thermal imaging, detecting the extracted image features, and identifying different defect types.

9. The dock folding structure design and manufacturing system based on artificial intelligence and machine vision according to claim 8 is characterized in that: The real-time detection of printing defects using infrared thermal imaging method also includes: extracting image features of infrared thermal imaging corresponding to the defect according to the defect position, extracting time series signals of different defects using wavelet transform, and analyzing the differences in time series signals of different defects, so as to more accurately identify different defect types.

10. The dock folding structure design and manufacturing system based on artificial intelligence and machine vision according to claim 8 is characterized in that: The method of performing X-ray nondestructive testing on the dock folded structure and obtaining internal structure defect parameters includes: performing X-ray nondestructive testing on the dock folded structure, obtaining X-ray images, and obtaining size parameters of pore defects using computer vision image processing methods.

Images