AR-based ship weld detection method, terminal and medium

Abstract

The application provides an AR-based ship weld detection method, a terminal and a medium, the method comprising: acquiring ship model information in a work area, weld model information of a weld, and weld process requirements; based on coordinate information of a positioning mark, registering the ship model to the work area and superimposing each weld model on the ship model; using an AR device to extract morphological feature information of each weld model; based on the weld process requirements and the morphological feature information of each weld model, performing weld detection on each weld model to obtain weld detection results of each weld model, thereby effectively improving the detection efficiency of ship welds.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of detection, in particular to an AR-based ship weld detection method, a terminal and a computer storage medium. BACKGROUND

[0002] Ship welding, as a major system engineering in shipbuilding, its production runs through the entire cycle of shipbuilding. According to the shipbuilding, it is divided into different levels such as total section, sub-section, large assembly, medium assembly, small assembly, etc. Ship welding is also divided into different levels. Since the quality of ship welds will directly affect the service life of the ship, in order to ensure the quality of ship welds, shipbuilding enterprises often need to control the quality of each weld of each product at all levels of the ship; the quality control mainly includes the "self-inspection" of the production personnel after the completion of the weld and the "external inspection" control of the weld by the quality inspection personnel (ship owner, ship inspection, quality inspection group, etc.).

[0003] However, whether it is self-inspection or external inspection, visual detection is currently the main method, and automatic detection has not yet been realized. Not only is the accuracy of the detection result low, but also the efficiency of quality inspection is low.

[0004] In addition, due to the large area covered by the intermediate products at all levels in shipbuilding, the quality inspection personnel often need to go to the place where each intermediate product is placed to perform the inspection of the weld quality, and the travel time spent on the round trip may even be longer than the quality inspection time, resulting in a decrease in the efficiency of the quality inspection of the ship weld; and since the self-inspection process and the external inspection process are completely independent, the external inspection of the product weld is usually performed after the self-inspection of the product weld is completed, the execution times of the two are staggered and not synchronized, so the result of the self-inspection cannot be transmitted to the external inspection personnel synchronously; when the external inspection personnel finds a problem, the self-inspection personnel usually have completed the inspection of the previous product weld, and then need to return to the previous product to re-inspect, resulting in repeated execution of the quality inspection work, thereby further reducing the efficiency of the quality inspection of the ship weld, and making the progress of the quality inspection of the ship weld unable to match the current shipbuilding progress. SUMMARY

[0005] In view of the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide an AR-based ship weld detection method, a terminal and a computer storage medium, which can solve the problem of low automation degree in the existing ship weld quality inspection work, resulting in low efficiency of weld quality inspection.

[0006] To achieve the above object and other related objects, the present application provides, in a first aspect, an AR-based ship weld detection method for detecting each weld in a work area by using an AR device; wherein the work area is provided with a positioning mark; the AR-based ship weld detection method comprises: acquiring ship model information in the work area, weld model information of each weld, and weld process requirements; collecting coordinate information of the positioning mark, registering the ship model to the work area based on the coordinate information of the positioning mark, and superimposing each weld model on the ship model; extracting morphological feature information of each weld model by using the AR device; and performing weld detection on each weld model based on the weld process requirements and the morphological feature information of each weld model to obtain weld detection results of each weld model.

[0007] In an embodiment of the present application, the weld process requirements are associated with a ship part in the ship model, and the weld detection on each weld model based on the weld process requirements and the morphological feature information of each weld model comprises: determining that the weld model is superimposed on the ship part in the ship model; determining the weld process requirements corresponding to the ship part according to the ship part; and detecting whether the morphological feature information of the weld model conforms to the weld process requirements based on the weld process requirements to obtain the weld detection result of the weld model.

[0008] In an embodiment of the present application, the AR device is connected to each network user terminal, and the weld detection on each weld model based on the weld process requirements and the morphological feature information of each weld model comprises: performing a self-checking process on each weld model by using the AR device according to the weld process requirements to obtain a self-checking result of each weld model; collecting a video of the self-checking process by using the AR device while performing the self-checking process, so that each network user terminal performs an external checking process on each weld model that passes the self-checking based on the video of the self-checking process to obtain an external checking result of the weld model; and obtaining the weld detection result of each weld model based on the self-checking result and the external checking result corresponding to each weld model.

[0009] In an embodiment of the present application, the weld process requirements include a preset weld width range and a weld flatness range, and the self-checking process performed on each weld model by using the AR device comprises: comparing width information of the weld model with the preset weld width range and comparing flatness information of the weld model with the preset weld flatness range by using the AR device; when the width information of the weld model is less than the weld width range and the flatness information of the weld model is less than the weld flatness range, it is determined that the weld model passes the self-checking, otherwise, it is determined that the weld model fails the self-checking.

[0010] In an embodiment of the present application, each network user terminal performs an external inspection process on each weld model that passes the self-inspection process based on the video of the self-inspection process, including: each network user terminal checks whether each operation in the self-inspection process meets the preset self-inspection specification based on the video of the self-inspection process; if yes, the network user terminal sets the weld model that passes the self-inspection as passing the external inspection; if no, the network user terminal obtains the weld model that passes the self-inspection but does not meet the self-inspection specification, sets it as failing the mutual inspection, and feeds back the information of the weld model that fails the external inspection to the AR device.

[0011] In an embodiment of the present application, each network user terminal performs an external inspection process on each weld model that passes the self-inspection process based on the video of the self-inspection process, including: each network user terminal checks whether each operation in the self-inspection process meets the preset self-inspection specification based on the video of the self-inspection process; if yes, the network user terminal sets the weld model that passes the self-inspection as passing the external inspection; if no, the network user terminal obtains the weld model that passes the self-inspection but does not meet the self-inspection specification, sets it as failing the mutual inspection, and feeds back the information of the weld model that fails the external inspection to the AR device.

[0012] In an embodiment of the present application, the AR-based ship weld detection method further includes: for the weld model that fails the detection, connecting the AR device to a flaw detection device to perform flaw detection on the weld corresponding to the weld model based on the flaw detection device, including: a flaw detection personnel uses the flaw detection device to perform flaw detection on a plurality of flaw detection points on the weld, and transmits the flaw detection result to the AR device in real time; wherein the flaw detection result includes position information of each flaw detection point and flaw detection information of the corresponding position; performing flaw detection self-inspection on the weld using the AR device, including: displaying each flaw detection point on the weld model according to the position information of the flaw detection point; checking whether the flaw detection value corresponding to each flaw detection point meets the standard; if yes, setting the weld model where the flaw detection point is located as passing the flaw detection self-inspection; if no, setting the weld model where the flaw detection point is located as failing the flaw detection self-inspection, and sending the weld model that fails the flaw detection self-inspection and each flaw detection point information superimposed on the weld model to the construction personnel.

[0013] In an embodiment of the present application, the flaw detection based on the flaw detection equipment performing flaw detection on the weld corresponding to the weld model further comprises: during the self-inspection process, using the AR equipment to collect the self-inspection process as a video, and sending the video to each network user terminal, so that each network user terminal detects whether each operation in the self-inspection process meets the self-inspection specification according to the video of the self-inspection process, and if so, sets each weld model that passes the self-inspection as a mutual inspection pass, and if not, obtains the weld model that passes the self-inspection but does not meet the self-inspection specification, and sets it as a mutual inspection fail; and the network user terminal feeds back the weld model information that fails the external inspection to the AR equipment.

[0014] In a second aspect, the present application provides a terminal, comprising: a processor and a memory, the memory being in communication connection with the processor; the memory is used for storing a computer program, and the processor is used for executing the computer program stored in the memory, so that the terminal executes the AR-based ship weld detection method as described above.

[0015] In a third aspect, the present application further provides a computer storage medium, which stores a computer program, and the computer program is executed by a processor to execute the AR-based ship weld detection method as described above.

[0016] As described above, the AR-based ship weld detection method, terminal and computer storage medium provided by the present application use the AR equipment to extract the shape feature information of each weld model, perform weld detection on each weld model based on the weld process requirements and the shape feature information of each weld model, and obtain the detection result of each weld, so that the process requirements and the detection result corresponding to each weld can be displayed in the augmented reality environment, so that the detection personnel can intuitively and quickly obtain the process requirements and the detection result of the weld, and then can efficiently check the process requirements, feed back the detection result and perform subsequent steps, thereby realizing the automation level of ship weld detection and greatly improving the detection efficiency of ship welds. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 FIG. 1 shows a structural schematic diagram of the AR equipment provided by an embodiment of the present application;

[0018] Figure 2 FIG. 4 shows a flowchart of the AR-based ship weld detection method provided by the present application in an embodiment;

[0019] Figure 3 FIG. 6 shows a flowchart of step S300 in the AR-based ship weld detection method provided by the present application in an embodiment;

[0020] Figure 4 A flowchart of another embodiment of the AR-based ship weld detection method provided by the present application is shown;

[0021] Figure 5 A structural diagram of the terminal provided by an embodiment of the present application is shown

[0022] Element number explanation

[0023] 800 AR device

[0024] 801 Sensor unit

[0025] 802 Display unit

[0026] 803 Feature extraction unit

[0027] 804 Acquisition unit DETAILED DESCRIPTION

[0028] The present application will be described in greater detail by way of specific embodiments, which should not be construed as limiting the present application. Other advantages and benefits of the present application will be apparent to those skilled in the art upon reading the description of the embodiments. The present application can be implemented or applied in other different embodiments, and the details in the description can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be noted that the embodiments below and the features in the embodiments can be combined with each other without conflict.

[0029] It should be noted that the diagrams provided in the following embodiments only schematically illustrate the basic concept of the present application, and the diagrams.

[0030] The existing ship weld detection method has a low level of automation, resulting in low detection efficiency and other problems. To improve the detection efficiency of ship weld detection, an AR-based ship weld detection method is provided in an embodiment of the present application, which is suitable for an AR device to realize detection of each weld in a work area by using the AR device.

[0031] As shown in the figure, the AR device includes a sensor unit 801, a display unit 802, a feature extraction unit 803, and an acquisition unit 804. The sensor unit 801 is configured to sense a positioning mark in the work area to obtain positioning information of the AR device relative to the work area based on the positioning mark. The display unit 802 is configured to display each model information in three dimensions to generate a virtual scene of augmented reality in the AR device. The feature extraction unit 803 is configured to extract morphological feature information contained in each model according to the model information displayed in the display unit. The acquisition unit 804 is configured to acquire each image displayed in the display unit to obtain each acquisition image or generate an acquisition video based on the images acquired at each time. Figure 1 ​

[0032] Referring to Figure 2 , a flowchart of an embodiment of the AR-based ship weld detection method provided by the embodiment of the present application is shown.

[0033] As Figure 2 shown, the AR-based ship weld detection method comprises:

[0034] S100, determining a work area to be detected, and acquiring ship section model information in the work area, weld model information of a weld, and weld process requirements;

[0035] The ship section model information is three-dimensional model information of a ship body assembly of the ship in the work area.

[0036] The weld model information is three-dimensional model information of a weld surface shape distribution of the weld.

[0037] The weld process requirements are that a shape distribution feature of the weld is located in a numerical range corresponding to the shape distribution feature of the weld. In a specific embodiment, the weld process requirements include a preset weld width range and a weld flatness range.

[0038] Specifically, after determining the work area to be detected, the server transmits weld detection data of the work area to the AR device according to the work area information, including ship model information of the work area, weld model information, and weld process requirements.

[0039] The weld model information is three-dimensional information of each weld collected by a construction worker after each weld in the work area is completed, so as to construct a weld model corresponding to each weld based on the three-dimensional information of each weld, and store each weld model in the server.

[0040] In a specific implementation, after the construction worker completes welding of all the welds in the work area, the work area is set as the work area to be detected, and the work area information and the weld model information of each weld in the work area are uploaded to the server. The information of the work area includes ship model information of the work area and weld process requirements. The server sends a weld detection instruction of the work area to the self-inspection worker, and sends the weld detection data related to the work area to the AR device, so that the self-inspection worker performs weld self-inspection work of the work area by using the AR device.

[0041] S200, acquiring coordinate information of a positioning mark, and registering the ship model in the work area based on the coordinate information of the positioning mark, and superimposing each weld model on the ship model.

[0042] The positioning identifier is an identifier pre-set in the work area and used for realizing positioning of the AR model. In a specific embodiment, the self-inspection personnel pre-acquire the position of the positioning identifier in the work area, and attach the positioning identifier at the corresponding position of the work area. For example, the positioning identifier is a positioning two-dimensional code with a size of 25 cm*25 cm.

[0043] Specifically, the self-inspection personnel wears the AR device, scans the pre-set positioning identifier of the work area by using a sensor unit in the AR device, to obtain coordinate information corresponding to the positioning identifier; based on the coordinate information, position information of the AR device relative to the work area is determined; based on the position information of the AR device relative to the work area and the coordinate information of the ship model, spatial registration is performed on the ship model, so that the ship model is registered with the work area, and the registered ship model is displayed in a display unit of the AR device, thereby generating an augmented reality scene of the AR device; and based on the positional relationship between the weld models and the ship model, each weld model is superimposed and displayed at a corresponding position of the ship model.

[0044] Further, each weld model to be detected in the work area is rendered and displayed; for example, an undetected weld model is rendered and displayed as red in the display unit of the AR device, and a detected weld is rendered and displayed as gray, so as to prevent omission in the weld detection process.

[0045] S300, the shape feature information of each weld model is extracted by using the AR device; based on the weld process requirement and the shape feature information of each weld model, weld detection is respectively performed on each weld model, to obtain a weld detection result of each weld model.

[0046] The weld detection includes a self-inspection process performed by the self-inspection personnel through the AR device, and an external inspection process performed by each external inspection personnel through the network user terminal.

[0047] In this embodiment, step S300 includes the following sub-steps when specifically executed, as shown in the following table: Figure 3

[0048] S301, the shape feature information of each weld model is extracted; and based on the weld process requirement, a self-inspection process is performed on each weld model by using the AR device, to obtain a self-inspection result of each weld model.

[0049] The weld process requirement includes a pre-set weld width range and a pre-set weld flatness range.

[0050] ​Specifically, a single weld model is selected as a current weld to be detected; after starting the weld detection process, the inspector displays the weld based on an AR interaction instruction and controls a feature extraction unit in the AR device to extract width information and flatness information of the weld model; and the AR device is used to compare the width information of the weld with a preset weld width range and compare the flatness information of the weld with a preset weld flatness range; when the weld width information is less than the preset weld width range and the weld flatness information is less than the preset weld flatness range, it is determined that the weld model is self-inspected qualified, otherwise, it is determined that the weld model is self-inspected unqualified; the above self-inspection process is performed on each weld model in the work area to obtain the weld self-inspection result of each weld model in the work area.

[0051] Optionally, after obtaining the weld self-inspection result of each weld model, the process requirement corresponding to each weld model and the weld self-inspection result are displayed in the augmented reality environment, so that the inspector can efficiently obtain the process requirement of the weld model and the defects existing in the weld according to the process requirement.

[0052] S302, while performing the self-inspection process on each weld model, a video of the self-inspection process is collected by using the AR device; based on the video of the self-inspection process, each network user end performs an external inspection process on each weld model that is self-inspected qualified to obtain an external inspection result of the weld model;

[0053] Specifically, while performing the self-inspection process on each weld model, the inspector collects a video of the self-inspection process by using a collection unit in the AR device, and sends the video of the self-inspection process to the network user end, so that each network user end checks whether each operation in the self-inspection process conforms to a preset self-inspection specification based on the video; if yes, the network user end sets the weld model that is self-inspected qualified as externally inspected qualified, otherwise, the network user end sets the weld model that is self-inspected qualified as externally inspected unqualified, and feeds back the information of the weld model that is externally inspected unqualified to the inspector, so that the inspector re-performs the self-inspection process on the weld model that is externally inspected unqualified.

[0054] It should be noted that in other embodiments, the step S301 and the step S302 can also be synchronously performed, that is, the step S302 is performed while the step S301 is performed.

[0055] S303, based on the self-inspection result and the external inspection result corresponding to each weld model, a weld detection result of each weld model is obtained.

[0056] Specifically, for a single weld model, when its corresponding self-inspection result is self-inspection qualified, and when its corresponding external inspection result is external inspection qualified, it is determined that the weld model is weld inspection qualified, that is, the detection result of the weld corresponding to the weld model is set to be inspection qualified; otherwise, it is determined that the weld model is inspection unqualified, that is, the detection result of the weld corresponding to the weld model is set to be inspection unqualified.

[0057] Optionally, the self-inspection personnel performs the self-inspection process on each weld model, and further includes: when it is determined that the weld model is self-inspection unqualified, the self-inspection personnel uses the acquisition unit in the AR device to take a photo of the weld model that is self-inspection unqualified, and synchronously uploads the weld photo to the server to notify the weld construction personnel to rectify; when it is determined that the weld model is self-inspection qualified, the self-inspection personnel uses the AR device to upload the self-inspection personnel information and the self-inspection result to the server.

[0058] Optionally, the server further sends the weld process requirement to each network user end, and in the execution step S300, when each network user end checks whether each operation in the weld self-inspection process is standardized based on the video of the self-inspection process, it further checks whether the morphological characteristics of each weld model meet the weld process requirement; if yes, the network user end sets the self-inspection qualified weld model to be external inspection qualified; if not, the network user end sets the self-inspection qualified weld model to be external inspection unqualified, so as to realize the external inspection of each weld model in the work area, and improve the accuracy of weld detection.

[0059] In another embodiment, the AR-based ship weld detection method, as shown in Figure 4 after the execution step S300, further includes:

[0060] S400, for the weld model whose weld detection result is inspection unqualified, connecting the AR device to the flaw detection device to perform flaw detection on the weld corresponding to the weld model based on the flaw detection device, so as to obtain the flaw detection result of the weld.

[0061] The AR device is connected to the flaw detection device.

[0062] Specifically, when it is detected that there is a weld model that is inspection unqualified in the work area, the weld corresponding to the weld model is set to be a weld to be checked; the self-inspection personnel controls the AR device to send an instruction to the flaw detection device based on the AR interaction instruction, so that the AR device is connected to the flaw detection device; the flaw detection personnel performs flaw detection on the weld to be checked by using the flaw detection device.

[0063] In a specific embodiment, after the AR device is connected to the flaw detection device, the flaw detection personnel selects a plurality of flaw detection points on the weld to be checked using the flaw detection device for flaw detection, and transmits the flaw detection results to the AR device in real time to display the flaw detection results on the display unit of the AR device; wherein the flaw detection results include position information of each flaw detection point and flaw detection information corresponding to the position.

[0064] After the AR device obtains the flaw detection results, the inspector performs a flaw self-inspection process on the weld using the AR device, including: displaying each flaw detection point on the weld model in the AR device display unit in the form of a bright spot according to the position information of the flaw detection points; detecting whether the flaw detection value corresponding to each flaw detection point meets the standard, and if so, setting the weld model where the flaw detection point is located as a flaw self-inspection qualified model, and if not, setting the weld model where the flaw detection point is located as a flaw self-inspection unqualified model, and sending the flaw self-inspection unqualified model and each flaw detection point information superimposed thereon to the weld construction personnel, so that the construction personnel correct the weld corresponding to the unqualified weld model.

[0065] Further, during the flaw self-inspection process, the acquisition unit in the AR device acquires the flaw self-inspection process as a video, and sends the video to each network user terminal, so that each network user terminal detects whether each operation in the flaw self-inspection process meets the self-inspection specification according to the video, and if so, sets each flaw self-inspection qualified weld model as a flaw mutual inspection qualified model, and if not, acquires the flaw self-inspection qualified weld model corresponding to the operation that does not meet the self-inspection specification, and sets it as a flaw mutual inspection unqualified model; and feeds back the flaw mutual inspection unqualified model to the AR device, so that the inspector re-performs the flaw self-inspection process on the flaw mutual inspection unqualified model.

[0066] To solve the technical problems in the prior art, the application also provides a terminal, please refer to Figure 5 , which shows a structure schematic diagram of the terminal provided by the embodiment of the application; as Figure 5 shown, the terminal 5 includes a memory 51 and a processor 52 connected to each other; the memory 51 is used to store a computer program, and the processor 52 is used to execute the computer program stored in the memory, so that the terminal executes the steps in the AR-based ship weld detection method.

[0067] Optionally, the number of the memory can be one or more, and the number of the processor can be one or more.

[0068] Optionally, the processor in the terminal loads one or more instructions corresponding to an application program according to the steps of the AR-based ship weld detection method described above into the memory, and runs the application program stored in the memory, so as to realize the functions in the AR-based ship weld detection method, which will not be repeated here.

[0069] It should be noted that the memory includes but is not limited to a random access memory (RAM), and can also include a non-volatile memory, such as at least one disk memory. Similarly, the processor can also be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0070] In addition, the embodiment of the present application also provides a computer readable storage medium, which stores a computer program, and the program is called by a processor to realize the AR-based ship weld detection method.

[0071] Among them, the computer readable storage medium can be a tangible device that maintains and stores instructions for use by an instruction execution device. The computer readable storage medium can be, for example but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any appropriate combination of the above. More specific examples (a non-exhaustive list) of the computer readable storage medium include a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device.

[0072] The computer readable program described herein can be downloaded from a computer readable storage medium to various computing / processing devices, or to external computers or external storage devices via networks, such as the Internet, local area networks, wide area networks and / or wireless networks. The network adapter or network interface in each computing / processing device receives the computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within each computing / processing device.

[0073] To sum up, the AR-based ship weld detection method, terminal and computer storage medium provided by the present application use an AR device to extract the shape feature information of each weld model, compare the shape feature information of the weld model with the pre-acquired weld process requirements, obtain the weld detection result of each weld based on the comparison result, and display the process requirements and detection results corresponding to each weld in an augmented reality environment, so that the detection personnel can intuitively and quickly obtain the process requirements and detection results of the weld, efficiently check the process requirements, feed back the detection results and perform subsequent steps, and the automatic detection of the ship weld is realized, the detection efficiency of the ship weld is improved, the AR device is connected to each network user end, the self-inspection of the weld model using the AR device is performed, and the external inspection is performed based on the collected self-inspection process video, so that the unqualified welds found in the external inspection process can be quickly and efficiently fed back to the self-inspection personnel, the time of the external inspection personnel in the rush is reduced, the self-inspection efficiency of the self-inspection personnel in the same work area is improved, and the quality inspection efficiency of the ship weld is greatly improved.

[0074] The above embodiments only exemplarily illustrate the principles and effects of the present application, and are not used to limit the present application. Any person skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes completed by those skilled in the art without departing from the spirit and technical thought disclosed by the present application should be covered by the claims of the present application.

Claims

1. An AR-based ship weld detection method, characterized by, The method comprises the following steps: The method comprises the following steps: Obtaining a ship model, a weld model and a weld process requirement in a work area; Registering the ship model to the work area based on the coordinate information of the positioning mark, and superimposing each weld model on the ship model; Extracting the shape feature information of each weld model by using the AR device; based on the weld process requirement and the shape feature information of each weld model, performing weld detection on each weld model to obtain the weld detection result of each weld model; The AR device is connected to each network user terminal, and the weld detection on each weld model based on the weld process requirement and the shape feature information of each weld model comprises: According to the weld process requirement, performing a self-checking process on each weld model by using the AR device to obtain a self-checking result of each weld model; while performing the self-checking process, collecting a video of the self-checking process by using the AR device, so that each network user terminal performs an external checking process on each weld model that passes the self-checking based on the video of the self-checking process to obtain an external checking result of the weld model; based on the self-checking result and the external checking result corresponding to each weld model, obtaining the weld detection result of each weld model.

2. The AR-based ship weld detection method of claim 1, wherein, The weld process requirement is associated with a ship part in the ship model, and the weld detection on each weld model based on the weld process requirement and the shape feature information of each weld model comprises: Determining the ship part in the ship model to which the weld model is superimposed; According to the ship part, determining the weld process requirement corresponding to the ship part; Based on the weld process requirement, detecting whether the shape feature information of the weld model conforms to the weld process requirement to obtain the weld detection result of the weld model.

3. The AR-based ship weld detection method of claim 1, wherein, The weld process requirement comprises a preset weld width range and a weld flatness range; the self-checking process performed on each weld model by using the AR device comprises: Comparing the width information of the weld model with the preset weld width range and the flatness information of the weld model with the preset weld flatness range by using the AR device; when the width information of the weld model is less than the weld width range and the flatness information of the weld model is less than the weld flatness range, it is determined that the weld model passes the self-checking, otherwise, it is determined that the weld model fails the self-checking.

4. The AR-based ship weld detection method of claim 1, wherein, The external checking process performed on each weld model that passes the self-checking by each network user terminal based on the video of the self-checking process comprises: Each of the network terminals checks whether each operation in the self-inspection process meets the preset self-inspection specification based on the video of the self-inspection process. If yes, the network terminal sets the self-inspection qualified weld model as the external inspection qualified. If no, the network terminal sets the self-inspection qualified weld model corresponding to the operation not meeting the self-inspection specification as the mutual inspection unqualified, and feeds back the information of the external inspection unqualified weld model to the AR device.

5. The AR-based ship weld detection method of claim 1, wherein, The network terminals perform the external inspection process on each self-inspection qualified weld model based on the video of the self-inspection process, and the network terminals further comprise: The network terminals check whether the shape feature of the weld model meets the weld process requirement based on the video of the self-inspection process. If yes, the network terminal sets the self-inspection qualified weld model as the external inspection qualified. If no, the network terminal sets the self-inspection qualified weld model as the external inspection unqualified.

6. The AR-based ship weld detection method of claim 1, wherein, Further comprising: For the weld model with the detection result of the detection unqualified, the AR device is connected to the flaw detection device to perform the flaw detection on the weld corresponding to the weld model based on the flaw detection device, and the method further comprises: The flaw detection personnel use the flaw detection device to perform the flaw detection on a plurality of flaw detection points on the weld, and transmit the flaw detection result to the AR device in real time. The flaw detection result comprises the position information of each flaw detection point and the flaw detection information of the corresponding position. The method for performing the flaw detection self-inspection process on the weld by using the AR device comprises: According to the position information of the flaw detection point, each flaw detection point is displayed on the weld model. If the flaw detection value corresponding to each flaw detection point meets the standard, the weld model where the flaw detection point is located is set as the flaw detection self-inspection qualified. If not, the weld model where the flaw detection point is located is set as the flaw detection self-inspection unqualified, and the weld model with the flaw detection self-inspection unqualified and the information of each flaw detection point superimposed on the weld model are transmitted to the construction personnel.

7. The AR-based ship weld detection method of claim 6, wherein, The method for performing the flaw detection on the weld corresponding to the weld model based on the flaw detection device further comprises: During the flaw detection self-inspection process, the AR device collects the flaw detection self-inspection process as a video, and transmits the video to each network terminal, so that each network terminal detects whether each operation in the flaw detection self-inspection process meets the self-inspection specification based on the video of the flaw detection self-inspection process. If yes, each flaw detection self-inspection qualified weld model is set as the flaw detection mutual inspection qualified. If not, the flaw detection self-inspection qualified weld model corresponding to the operation not meeting the self-inspection specification is set as the flaw detection mutual inspection unqualified. The network terminal feeds back the information of the external inspection unqualified weld model to the AR device.

8. A terminal, characterized by comprising: The method further comprises: A processor and a memory, the memory is in communication connection with the processor; The memory is used for storing a computer program, and the processor is used for executing the computer program stored in the memory, so that the terminal executes the AR-based ship weld detection method according to any one of claims 1 to 7.

9. A computer storage medium storing a computer program, the computer program comprising instructions, which, when executed on a computer, cause the computer to perform the method according to any one of claims 1 to 8. The computer program is executed by a processor to perform the AR-based ship weld detection method of any one of claims 1 to 7.

Images