Pipeline maintenance device and maintenance method based on AR intelligent identification

Abstract

The invention provides a pipeline maintenance device and method based on AR intelligent recognition. The device comprises AR equipment, a gesture input unit and a pipeline. The service valve is installed on the pipeline body, the service valve, the control motor and the second conveying unit are fixed in the protective cover, and the control motor is electrically connected with the second conveying unit; the camera is used for shooting a pipeline to obtain a first real-time image and shooting the gesture input unit based on a recognition result to obtain a second real-time image; the processor identifies and generates interaction information, the interaction information is displayed by the display unit, a control signal is obtained according to the second real-time image, and the first transmission unit and the second transmission unit are connected to form a first transmission channel; the control signal is transmitted through the first transmission channel, and the control motor controls the valve opening degree of the service valve according to the control signal. The safety valve can avoid harm to the environment or personnel caused by leakage of toxic liquid media, does not need to be in direct contact with a service valve during operation, and is easy to operate and long in service life.

Description

Technical Field

[0001] The present disclosure relates to the technical field of pipeline intelligent maintenance, and in particular to a pipeline maintenance device and maintenance method based on AR intelligent recognition. Background Art

[0002] Pipeline systems used to transport liquid media need to be maintained and overhauled regularly or irregularly, especially pipeline systems that transport toxic or corrosive liquid media. In order to make maintenance and overhaul work more convenient, an overhaul valve is usually installed in the pipeline system. During overhaul, the fluid flow is usually controlled or cut off through the overhaul valve. Maintenance personnel can control and adjust the fluid medium by controlling the opening of the overhaul valve to ensure the normal operation of other equipment, or isolate the faulty equipment by closing the overhaul valve to avoid affecting the entire system. At present, operators usually control the valve opening of the overhaul valve by rotating the handwheel or wrench. This method is simple and direct, but it depends on the skills and experience of the operator. When the operator operates improperly, and the overhaul valve is improperly maintained or aging and damaged, the medium will leak. The leakage of toxic liquid media is a serious industrial safety issue that may cause serious harm to the environment, personnel and production equipment. In addition, due to the harsh environment, the rotating handwheel of the overhaul valve is often covered with a layer of oil, which is not convenient for operation during maintenance. Summary of the invention

[0003] In response to the problems existing in the prior art, the present invention provides a pipeline inspection device based on AR intelligent recognition, which avoids environmental or personnel harm caused by leakage of toxic liquid media, does not require direct contact with the inspection valve, is simple to operate, and has a long service life.

[0004] To achieve the above-mentioned purpose, the technical solution adopted by the present disclosure is as follows: a pipeline maintenance device based on AR intelligent recognition, including an AR device, a gesture input unit and a pipeline; The AR device includes a camera, a processor, a display unit, a memory and a first transmission unit; the pipeline includes an AR tag, a pipeline body, a check valve, a control motor, a second transmission unit and a protective cover; The AR tag is used to store first identification information for identifying the pipeline; the memory is used to store second identification information for identifying the pipeline and gesture instructions; the inspection valve is installed on the pipeline body; the inspection valve, the control motor and the second transmission unit are all located in the protective cover, and the control motor is electrically connected to the second transmission unit; The camera is used to photograph the pipeline to obtain a first real-time image and transmit it to the processor, and to photograph the gesture input unit based on the recognition result to obtain a second real-time image and transmit it to the processor; at least one frame of the first real-time image contains the AR tag; The processor is used to call the second identification information, and identify the pipeline according to the second identification information and the first real-time image containing the AR tag and obtain an identification result, to generate interaction information, to control the first transmission unit to be connected with the second transmission unit and form a first transmission channel according to the identification result, and to call the gesture instruction and obtain a control signal according to the interaction information, the second real-time image and the gesture instruction; based on the identification result, the interaction information is generated according to the first real-time image, or the interaction information is generated according to the first real-time image and the second real-time image; the first transmission channel is a wireless transmission channel; the control signal is transmitted to the control motor through the first transmission channel, and the control motor is used to control the valve opening of the inspection valve according to the control signal; the display unit is used to display the interaction information.

[0005] In some of the embodiments, the pipeline further comprises a monitoring unit and a third transmission unit, and the monitoring unit is connected to the third transmission unit; When the identification result is that the processor identifies the pipeline: the processor controls the third transmission unit to connect with the second transmission unit to form a second transmission channel; The monitoring unit is used to obtain real-time information of the pipeline, and the real-time information is transmitted to the processor through the second transmission channel.

[0006] In some of these embodiments, the memory is further used to store historical information of the pipeline.

[0007] In some embodiments, the processor includes an image module, a numerical module, a recognition module, and a calculation processing module; The image module is used to preprocess the first real-time image and the second real-time image respectively, and transmit the preprocessed first real-time image or the second real-time image to the calculation processing module, and is used to preprocess the first real-time image containing the AR tag, and transmit the preprocessed first real-time image containing the AR tag to the recognition module; The recognition module is used to pre-process the AR tag to obtain decoding information, and transmit the decoding information to the calculation processing module; The numerical module is used to preprocess the real-time information and transmit the preprocessed real-time information to the calculation processing module; The calculation and processing module is used to generate the interaction information and transmit the interaction information to the display unit; The computing and processing module generates the interaction information according to the first real-time image based on the recognition result; or the computing and processing module generates the interaction information according to the first real-time image and the second real-time image based on the recognition result; or the computing and processing module obtains the interaction information according to the real-time information, the first real-time image and the second real-time image based on the recognition result; or the computing and processing module obtains the interaction information according to the real-time information and the first real-time image based on the recognition result; or the computing and processing module obtains the interaction information according to the real-time information, the first real-time image, the second real-time image and the historical information based on the recognition result; or the computing and processing module obtains the interaction information according to the real-time information, the first real-time image and the historical information based on the recognition result.

[0008] In some embodiments, the protective cover includes a first half cover, a second half cover and a stop valve; The first half cover is located on the upper side of the pipeline body, and the second half cover is located on the lower side of the pipeline body; a first opening is formed at the bottom of the first half cover, and a second opening is formed at the top of the second half cover; the bottom of the second half cover is funnel-shaped, and the stop valve is installed at the output end of the funnel; The first half cover and the second half cover clamp the pipeline body at the upper and lower sides of the pipeline body respectively, and the first opening matches the second opening; the control motor and the second transmission unit are located in the first half cover.

[0009] In some embodiments, the control motors are respectively fixed on the top walls of the first half covers.

[0010] A maintenance method is implemented using the pipeline maintenance device based on AR intelligent recognition, comprising the following steps: storing the first identification information on the AR tag; storing the second identification information and the gesture instruction in the memory; The first real-time image is obtained by photographing the pipeline with the camera; at least one frame of the first real-time image includes the AR tag; The processor calls the second identification information from the memory, identifies the pipeline according to the second identification information and the first real-time image containing the AR tag, and obtains the identification result; When the recognition result is an identification pipeline: the processor obtains the interaction information according to the first real-time image, and the interaction information is displayed through the display unit; the processor controls the first transmission unit to be connected to the second transmission unit, and a first transmission channel is formed between the first transmission unit and the second transmission unit; Obtaining a control requirement according to the interaction information; Based on the control requirement, using the camera to photograph the gesture input unit to obtain a second real-time image and transmitting the second real-time image to the processor; The processor updates the interaction information according to the second real-time image, and the updated interaction information is displayed through the display unit; The processor calls the gesture instruction from the memory, and obtains a control signal according to the updated interaction information, the second real-time image and the gesture instruction; The control signal is transmitted to the control motor located in the protective cover through the first transmission channel; The control motor controls the valve opening of the inspection valve according to the control signal.

[0011] In some embodiments, the interaction information includes first interaction information and second interaction information; when the recognition result is an identification pipeline: the processor obtains the interaction information as the first interaction information according to the first real-time image, and the processor updates the first interaction information according to the second real-time image to obtain the second interaction information.

[0012] In some embodiments, the step of obtaining the control signal is: When the control requirement is an input gesture: based on the control requirement, using the camera to photograph the gesture input unit to obtain a second real-time image and transmitting the second real-time image to the processor; The processor updates the first interaction information according to the second real-time image to obtain the second interaction information, and the second interaction information is displayed through the display unit; The processor obtains the inspection valve marking area and the hand marking area respectively according to the second interaction information; When the inspection valve mark area and the hand mark area at least partially overlap: performing gesture input through a gesture input unit and updating a second real-time image; The processor obtains a gesture image according to the updated second real-time image; the processor calls the gesture instruction from the memory, and obtains the control signal according to the gesture image and the gesture instruction.

[0013] In some embodiments, the step of obtaining the control signal is: When the control requirement is a gesture input: based on the control requirement, performing gesture input through a gesture input unit, and using the camera to photograph the gesture input unit to obtain a second real-time image and transmit the second real-time image to the processor; The processor updates the first interaction information according to the second real-time image to obtain the second interaction information, and the second interaction information is displayed through the display unit; The processor obtains a gesture image according to the second real-time image; the processor calls the gesture instruction from the memory, and obtains a preparation signal according to the gesture image and the gesture instruction; The processor obtains the inspection valve marking area and the hand marking area respectively according to the second interaction information; When the inspection valve mark area and the hand mark area at least partially overlap: the processor obtains the control signal according to the preparation signal.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The present disclosure sets a protective cover to prevent the leakage of toxic liquid media from causing harm to the environment, personnel and production equipment. The AR device accurately captures the real scene to achieve intuitive visual guidance. At the same time, with gestures, the virtual object can be intuitively understood and operated to complete the pipeline maintenance work, avoiding direct contact between the operator and the inspection valve and reducing the difficulty of operation. The present invention can protect the inspection valve by arranging a protective cover, avoid oil stains adhering to the inspection valve, increase the service life of the inspection valve, and avoid direct contact between operators and the inspection valve. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of the connection relationship of the pipeline maintenance device based on AR intelligent recognition disclosed in the present invention; Figure 2 It is a schematic diagram of the main perspective structure of the pipeline in the present disclosure; Figure 3 is a schematic diagram of the three-dimensional structure of the pipeline in the present disclosure; Figure 4 It is a three-dimensional perspective structural schematic diagram of the pipeline in the present disclosure; Figure 5 It is a schematic diagram of the top view of the pipeline in the present disclosure; Figure 6 It is a schematic diagram of the inspection valve marking area and the hand marking area in the present disclosure; Figure 7 It is a schematic diagram of the process of maintenance method I in the present disclosure; Figure 8 It is a schematic diagram of the process of maintenance method II in the present disclosure; Fig. 9 It is a schematic diagram of the process of maintenance method III in the present disclosure.

[0016] Among them, the figure markings are: 1. inspection valve; 2. control motor; 3. pipeline body; 4. protective cover; 41. first half cover; 42. second half cover; 43. connecting bolt; 44. stop valve; 45. connecting plate; 46. screw; 5. AR label; 6. inspection valve marking area; 7. hand marking area. DETAILED DESCRIPTION

[0017] In order to clearly illustrate the technical features of this solution, the following will be combined with the accompanying drawings and examples to describe in detail the implementation methods of this application, so that the application can fully understand how to use technical means to solve technical problems and achieve the corresponding technical effects and implement them accordingly. The embodiments of this application and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of this application.

[0018] See also Figure 1 , the embodiment of the present application provides a pipeline maintenance device based on AR intelligent recognition, including an AR device, a gesture input unit and a pipeline; preferably, the AR device is a wearable AR glasses, which frees the operator's hands and facilitates maintenance operations, and the gesture input unit is a hand, a wearable prosthetic hand, or a hand wearing a glove, etc.; The AR device includes a camera, a processor, a display unit, a memory and a first transmission unit; the pipeline includes an AR tag 5, a pipeline body 3, a check valve 1, a control motor 2, a second transmission unit and a protective cover 4; The AR tag 5 is used to store the first identification information of the identification pipeline; the memory is used to store the second identification information of the identification pipeline and the gesture instruction; the gesture instruction is the correspondence between the gesture and the control instruction, usually different gestures correspond to different control instructions, and the correspondence between the gesture and the control instruction can be preset and stored in the memory; The inspection valve 1 is installed on the pipeline body 3; preferably, the protective cover 4 is fixed on the pipeline body 3, and the inspection valve 1, the control motor 2 and the second transmission unit are all located in the protective cover 4. Preferably, the control motor 2 is fixed on the protective cover 4, and the control motor 2 is electrically connected to the second transmission unit. The control motor 2 and the second transmission unit are electrically connected in the protective cover 4, which can prevent the line from being directly exposed to the external environment, reduce the risk of line damage caused by external force, wear or animal gnawing, and reduce the frequency of replacement and maintenance; The camera is used to shoot the pipeline to obtain a first real-time image and transmit it to the processor, and to shoot the gesture input unit based on the recognition result to obtain a second real-time image and transmit it to the processor; at least one frame of the first real-time image contains an AR tag 5; The processor is used to call the second identification information, and identify the pipeline according to the second identification information and the first real-time image containing the AR tag 5 and obtain the identification result, to generate interaction information, to control the first transmission unit to be connected with the second transmission unit and form a first transmission channel according to the identification result, and to call the gesture instruction, and obtain the control signal according to the interaction information, the second real-time image and the gesture instruction; based on the identification result, the interaction information is generated according to the first real-time image, or the interaction information is generated according to the first real-time image and the second real-time image; the first transmission channel is a wireless transmission channel; the control signal is transmitted to the control motor 2 through the first transmission channel, and the control motor 2 is used to control the valve opening of the inspection valve 1 according to the control signal; the display unit is used to display the interaction information.

[0019] The working principle of the pipeline inspection device based on AR intelligent recognition disclosed in the present invention is: when pipeline inspection is required, the pipeline is photographed by the camera on the AR device to obtain a first real-time image and transmitted to the processor, the processor decodes the AR tag 5 according to the first real-time image containing the AR tag 5 to obtain the information to be identified stored in the AR tag 5, the processor calls the second identification information from the memory, and obtains the identification result according to the matching relationship between the second identification information and the first identification information in the AR tag 5. Preferably, the first real-time image is preprocessed before decoding, such as denoising, contrast enhancement, color correction, etc., to improve the accuracy of subsequent identification. When the recognition result is an identification pipeline: the processor generates interactive information based on the first real-time image and displays it on the display unit, and the processor controls the first transmission unit to connect with the second transmission unit to form a first transmission channel; at this time, the operator determines whether to input a gesture action based on the interactive information on the display unit. When a gesture needs to be input, the gesture is input through the gesture input unit, and the camera on the AR device shoots the gesture input unit to obtain a second real-time image and transmits it to the processor. The processor calls the gesture instruction from the memory and compares it with the gesture-related content in the second real-time image to obtain a control signal. The control signal is transmitted to the control motor 2 through the first transmission channel. The control motor 2 is used to control the valve opening of the inspection valve 1 according to the control signal. Since the first transmission channel can transmit the control signal to the protective cover 4 and control the control motor 2, and the inspection valve 1, the control motor 2 and the second transmission unit are respectively located in the protective cover 4, when the inspection valve 1 is damaged or the operator makes a mistake and causes the liquid medium to leak from the inspection valve 1, the protective cover 4 can collect the liquid medium to avoid the harm of the leakage of toxic liquid medium to the environment, personnel and production equipment. At the same time, the protective cover 4 can protect the inspection valve 1 to avoid the adhesion of oil stains on the inspection valve 1, thereby increasing the service life of the inspection valve 1. The control of the inspection valve 1 is executed by the control motor 2 under the control of the control signal, which can avoid direct contact between the operator and the inspection valve 1. The operator only needs to wear the AR device and combine it with gesture input. By accurately capturing the real scene to achieve intuitive visual guidance and cooperating with the pre-set gesture actions, he can intuitively understand and operate the virtual object to complete the pipeline maintenance work, avoiding direct contact between the operator and the inspection valve 1 and reducing the difficulty of operation.

[0020] In some of the embodiments, the pipeline further comprises a monitoring unit and a third transmission unit, the monitoring unit being connected to the third transmission unit; When the identification result is that the processor identifies the pipeline: the processor controls the third transmission unit to connect with the second transmission unit to form a second transmission channel; The monitoring unit is used to obtain real-time information of the pipeline, and the real-time information is transmitted to the processor through the second transmission channel.

[0021] The real-time information includes the real-time status data of the pipeline, such as the real-time flow, real-time pressure, and real-time liquid level. The real-time status data, i.e., the real-time information, obtained by the monitoring unit is transmitted to the processor through the second transmission channel, providing strong data support for maintenance.

[0022] In some embodiments, the memory is also used to store historical information of the pipeline, including the past operation status, maintenance records and possible problems of the pipeline. By analyzing this information, potential fault points can be found in time, providing data support for pipeline maintenance. In the event of an emergency in the pipeline, historical information can be used as a reference to help quickly locate the problem, shorten the troubleshooting time, and reduce accident losses; historical information also includes status information of the pipeline during normal operation. By comparing real-time information with historical information and displaying the results through a display unit, the maintenance process or results can be more intuitively displayed.

[0023] In some embodiments, the processor includes an image module, a numerical module, a recognition module, and a calculation processing module; the image, the numerical value, and the AR tag are pre-processed before being processed by the calculation processing module, which can improve the processing efficiency, enhance flexibility, and improve the processor performance; The image module is used to preprocess the first real-time image and the second real-time image respectively, and transmit the preprocessed first real-time image or the second real-time image to the calculation processing module, and is used to preprocess the first real-time image containing the AR tag, and transmit the preprocessed first real-time image containing the AR tag to the recognition module; the image module is used to perform preprocessing such as denoising, contrast enhancement, and color correction on the image data to improve the accuracy of subsequent recognition or calculation processing; further, the image module also performs preprocessing steps such as data cleaning, feature extraction, data conversion and standardization, data enhancement (optional), data formatting and correction on the gesture image to ensure the accuracy, consistency and comparability of the gesture data; The recognition module is used to pre-process the AR tag to obtain the decoded information and transmit the decoded information to the calculation processing module; the recognition module is used to pre-process the AR tag such as grayscale, binarization, decoding, data extraction, etc., so as to facilitate subsequent processing; The numerical module is used to preprocess real-time information and transmit the preprocessed real-time information to the calculation processing module; the numerical module is used to complete denoising, missing value, outlier and smoothing processing, data standardization, data conversion, etc. to ensure the accuracy and reliability of numerical data.

[0024] The calculation processing module is used to generate interaction information and transmit the interaction information to the display unit; The computing and processing module generates interaction information according to the first real-time image based on the recognition result; or the computing and processing module generates interaction information according to the first real-time image and the second real-time image based on the recognition result; or the computing and processing module obtains interaction information according to the real-time information, the first real-time image and the second real-time image based on the recognition result; or the computing and processing module obtains interaction information according to the real-time information and the first real-time image based on the recognition result; or the computing and processing module obtains interaction information according to the real-time information, the first real-time image, the second real-time image and historical information based on the recognition result; or the computing and processing module obtains interaction information according to the real-time information, the first real-time image and historical information based on the recognition result.

[0025] The real-time information is fused with the first real-time image to form interactive information, or the real-time information is fused with the first real-time image and the second real-time image to form interactive information. The real-time status of the pipeline can be intuitively understood through the interactive information, providing strong support for maintenance; In addition to displaying pipeline and real-time status data in the form of virtual augmented reality, interactive information can also be combined with historical information to form a comparison of real-time status data and historical information, fault details, maintenance references and other information to further improve maintenance efficiency.

[0026] In some embodiments, the memory includes a database, and the database is divided into a first database, a second database, and a third database according to the category of data, the first database is used to store gesture instructions, the second memory is used to store second identification information, and the third database is used to store historical information. Storing different data by category helps to improve data management efficiency and data security, and also helps to optimize data retrieval speed, strengthen the maintenance of data integrity and consistency, facilitate data analysis, and promote database scalability.

[0027] See also Figure 3 , 4 In some embodiments, the protective cover 4 includes a first half cover 41, a second half cover 42 and a stop valve 43. The protective cover 4 adopts a split structure, which is simple in structure and convenient for disassembly and assembly. When the stop valve 43 is set, when the liquid medium or the toxic liquid medium is retained in the protective cover 4, it can be discharged in time through the stop valve 43 for collection and treatment without disassembling the protective cover 4; The first half cover 41 is located on the upper side of the pipeline body 3, and the second half cover 42 is located on the lower side of the pipeline body 3; the first half cover 41 has a first opening at the bottom, and the second half cover 42 has a second opening at the top; the bottom of the second half cover 42 is funnel-shaped, and the stop valve 43 is installed at the output end of the funnel to facilitate the discharge and collection of liquid medium or toxic liquid medium; The first half cover 41 and the second half cover 42 clamp the pipeline body 3 at the upper and lower sides of the pipeline body 3, respectively, and the first opening matches the second opening, and a closed space is formed between the first half cover 41 and the second half cover 42, and the pipeline body 3 runs through the closed space; the control motor 2 and the second transmission unit are located in the first half cover 41. The control motor 2 and the second transmission unit are arranged in the first half cover 41 located on the upper side of the pipeline body 3, which can avoid contamination of the control motor 2 or the second transmission unit when the liquid medium or the toxic liquid medium leaks, thereby improving the service life.

[0028] Preferably, the first half cover 41 and the second half cover 42 are both made of transparent materials, so that the operating status of the inspection valve 1 and the control motor 2 and the real-time status inside the protective cover 4 can be intuitively seen.

[0029] In some embodiments, the control motor 2 is fixed on the top wall of the first half cover 41, so that the control motor 2 and the second transmission unit are away from the possible leakage position. During installation, after the control motor 2 is connected to the inspection valve 1, the first half cover 41 and the second half cover 42 are clamped and connected to the pipeline body 3 from the upper and lower sides of the pipeline body 3, and then the first half cover 41 is connected by screws 46; See also Figure 2 , 5 Preferably, a connecting plate 45 is provided on the outer wall of the top plate of the first half cover 41, and the screws 46 are connected to the control motor 2 through the connecting plate 45 and the top plate of the first half cover 41 in sequence, which can increase the thickness of the top plate and improve the connection strength between the control motor 2 and the first half cover 41.

[0030] Still see Figure 3 , 4 In some embodiments, the first half cover 41 and the second half cover 42 are fixedly connected by a connecting bolt 44 to facilitate disassembly and assembly. Preferably, the first opening edge and the second opening edge are bent outward, and a connecting hole is provided at the outward bending part, and the connecting bolt 44 connects the first half cover 41 and the second half cover 42 through the connecting hole.

[0031] See also Figure 7 The embodiment of the present application also provides a maintenance method, which is implemented by using a pipeline maintenance device based on AR intelligent recognition, and includes the following steps: The first identification information is stored in the AR tag 5; the second identification information and the gesture command are stored in the memory; A first real-time image is obtained by using a camera shooting pipeline; at least one frame of the first real-time image includes an AR tag 5; The processor calls the second identification information from the memory, recognizes the pipeline according to the second identification information and the first real-time image containing the AR tag, and obtains a recognition result; When the recognition result is an identification pipeline: the processor obtains interaction information according to the first real-time image, and the interaction information is displayed through the display unit; the processor controls the first transmission unit to be connected to the second transmission unit, and a first transmission channel is formed between the first transmission unit and the second transmission unit; Obtain control requirements based on interactive information; Based on the control requirements, a camera is used to shoot the gesture input unit to obtain a second real-time image and transmit it to the processor; The processor updates the interaction information according to the second real-time image, and the updated interaction information is displayed through the display unit; The processor calls the gesture instruction from the memory, and obtains a control signal according to the updated interaction information, the second real-time image and the gesture instruction; The control signal is transmitted to the control motor 2 located in the protective cover 4 through the first transmission channel; The control motor 2 controls the valve opening of the inspection valve 1 according to the control signal.

[0032] Preferably, the interaction information includes first interaction information and second interaction information; when the recognition result is an identification pipeline: the processor obtains the interaction information as the first interaction information according to the first real-time image, and the processor updates the first interaction information according to the second real-time image to obtain the second interaction information.

[0033] See also Figure 8 In some embodiments, the step of obtaining the control signal is: When the control requirement is an input gesture: based on the control requirement, a camera is used to shoot the gesture input unit to obtain a second real-time image and transmit it to the processor; The processor updates the first interaction information according to the second real-time image to obtain second interaction information, and the second interaction information is displayed through the display unit; See also Figure 6 , the processor obtains the inspection valve mark area 6 and the hand mark area 7 respectively according to the second interactive information; When the inspection valve marking area 6 and the hand marking area 7 at least partially overlap: perform gesture input through the gesture input unit and update the second real-time image; preferably, when the inspection valve marking area 6 and the hand marking area 7 at least partially overlap, the overlapping portion accounts for more than 50% of the hand marking area 7 or the overlapping portion accounts for more than 50% of the inspection valve marking area 6, that is, when the overlapping portion accounts for more than 50% of the hand marking area 7 or the overlapping portion accounts for more than 50% of the inspection valve marking area 6, it is considered that the inspection valve marking area 6 and the hand marking area 7 at least partially overlap; The processor obtains a gesture image according to the updated second real-time image; the processor calls a gesture instruction from the memory, and obtains a control signal according to the gesture image and the gesture instruction.

[0034] See also Fig. 9In some embodiments, the step of obtaining the control signal is: When the control requirement is a gesture input: based on the control requirement, a gesture input is performed through the gesture input unit, and a second real-time image is obtained by photographing the gesture input unit with a camera and transmitted to the processor; The processor updates the first interaction information according to the second real-time image to obtain second interaction information, and the second interaction information is displayed through the display unit; The processor obtains a gesture image according to the second real-time image; the processor calls a gesture instruction from the memory, and obtains a preparatory signal according to the gesture image and the gesture instruction; See also Figure 6 , the processor obtains the inspection valve mark area 6 and the hand mark area 7 respectively according to the second interactive information; When the inspection valve marking area and the hand marking area at least partially overlap: the processor obtains a control signal according to the preparation signal.

[0035] Finally, it should be noted that the above content is only used to illustrate the technical solution of the present invention, rather than to limit the scope of protection of the present invention. Simple modifications or equivalent substitutions of the technical solution of the present invention by ordinary technicians in this field do not deviate from the essence and scope of the technical solution of the present invention.

Claims

1. A pipeline maintenance device based on AR intelligent recognition, characterized in that: It includes an AR device, a gesture input unit and a pipeline; the AR device includes a camera, a processor, a display unit, a memory and a first transmission unit; the pipeline includes an AR tag, a pipeline body, a check valve, a control motor, a second transmission unit and a protective cover; The AR tag is used to store first identification information for identifying the pipeline; the memory is used to store second identification information for identifying the pipeline and gesture instructions; the inspection valve is installed on the pipeline body; the inspection valve, the control motor and the second transmission unit are all located in the protective cover, and the control motor is electrically connected to the second transmission unit; The camera is used to photograph the pipeline to obtain a first real-time image and transmit it to the processor, and to photograph the gesture input unit based on the recognition result to obtain a second real-time image and transmit it to the processor; at least one frame of the first real-time image contains the AR tag; The processor is used to call the second identification information, identify the pipeline according to the second identification information and the first real-time image containing the AR tag and obtain an identification result, generate interaction information, control the first transmission unit to connect with the second transmission unit and form a first transmission channel according to the identification result, and call the gesture instruction and obtain a control signal according to the interaction information, the second real-time image and the gesture instruction; Based on the recognition result, generating the interaction information according to the first real-time image, or generating the interaction information according to the first real-time image and the second real-time image; The first transmission channel is a wireless transmission channel; The control signal is transmitted to the control motor through the first transmission channel, and the control motor is used to control the valve opening of the inspection valve according to the control signal; the display unit is used to display the interactive information.

2. According to claim 1, the pipeline maintenance device based on AR intelligent recognition is characterized in that: The pipeline further comprises a monitoring unit and a third transmission unit, wherein the monitoring unit is connected to the third transmission unit; When the identification result is that the processor identifies the pipeline: the processor controls the third transmission unit to connect with the second transmission unit to form a second transmission channel; The monitoring unit is used to obtain real-time information of the pipeline, and the real-time information is transmitted to the processor through the second transmission channel.

3. The pipeline maintenance device based on AR intelligent recognition according to claim 2 is characterized in that: The memory is also used to store historical information of the pipeline.

4. The pipeline maintenance device based on AR intelligent recognition according to claim 3 is characterized in that: The processor includes an image module, a numerical module, a recognition module and a calculation processing module; The image module is used to preprocess the first real-time image and the second real-time image respectively, and transmit the preprocessed first real-time image or the second real-time image to the calculation processing module, and is used to preprocess the first real-time image containing the AR tag, and transmit the preprocessed first real-time image containing the AR tag to the recognition module; The recognition module is used to pre-process the AR tag to obtain decoding information, and transmit the decoding information to the calculation processing module; The numerical module is used to preprocess the real-time information and transmit the preprocessed real-time information to the calculation processing module; The calculation and processing module is used to generate the interaction information and transmit the interaction information to the display unit; The calculation processing module generates the interaction information according to the first real-time image based on the recognition result; or the computing and processing module generates the interaction information according to the first real-time image and the second real-time image based on the recognition result; or the computing and processing module obtains interaction information according to the real-time information, the first real-time image and the second real-time image based on the recognition result; or the computing and processing module obtains interactive information according to the real-time information and the first real-time image based on the recognition result; or the computing and processing module obtains interaction information based on the recognition result and according to the real-time information, the first real-time image, the second real-time image and the historical information; Or the computing and processing module obtains interaction information based on the recognition result, the real-time information, the first real-time image and the historical information.

5. The pipeline maintenance device based on AR intelligent recognition according to claim 1 is characterized in that: The protective cover comprises a first half cover, a second half cover and a stop valve; The first half cover is located on the upper side of the pipeline body, and the second half cover is located on the lower side of the pipeline body; a first opening is formed at the bottom of the first half cover, and a second opening is formed at the top of the second half cover; the bottom of the second half cover is funnel-shaped, and the stop valve is installed at the output end of the funnel; The first half cover and the second half cover clamp the pipeline body at the upper and lower sides of the pipeline body respectively, and the first opening matches the second opening; the control motor and the second transmission unit are located in the first half cover.

6. The pipeline maintenance device based on AR intelligent recognition according to claim 5 is characterized in that: The control motors are respectively fixed on the top walls of the first half covers.

7. A maintenance method, implemented by using the pipeline maintenance device based on AR intelligent recognition according to any one of claims 1 to 6, characterized in that: The following steps are involved: storing the first identification information on the AR tag; storing the second identification information and the gesture instruction in the memory; The first real-time image is obtained by photographing the pipeline with the camera; at least one frame of the first real-time image includes the AR tag; The processor calls the second identification information from the memory, identifies the pipeline according to the second identification information and the first real-time image containing the AR tag, and obtains the identification result; When the recognition result is an identification pipeline: the processor obtains the interaction information according to the first real-time image, and the interaction information is displayed through the display unit; the processor controls the first transmission unit to be connected to the second transmission unit, and a first transmission channel is formed between the first transmission unit and the second transmission unit; Obtaining a control requirement according to the interaction information; Based on the control requirement, using the camera to photograph the gesture input unit to obtain a second real-time image and transmitting the second real-time image to the processor; The processor updates the interaction information according to the second real-time image, and the updated interaction information is displayed through the display unit; The processor calls the gesture instruction from the memory, and obtains a control signal according to the updated interaction information, the second real-time image and the gesture instruction; The control signal is transmitted to the control motor located in the protective cover through the first transmission channel; The control motor controls the valve opening of the inspection valve according to the control signal.

8. The maintenance method according to claim 7, characterized in that: The interaction information includes first interaction information and second interaction information; when the recognition result is an identification pipeline: the processor obtains the interaction information as the first interaction information according to the first real-time image, and the processor updates the first interaction information according to the second real-time image to obtain the second interaction information.

9. The maintenance method according to claim 8, characterized in that: The steps of obtaining the control signal are: When the control requirement is an input gesture: based on the control requirement, using the camera to photograph the gesture input unit to obtain a second real-time image and transmitting the second real-time image to the processor; The processor updates the first interaction information according to the second real-time image to obtain the second interaction information, and the second interaction information is displayed through the display unit; The processor obtains the inspection valve marking area and the hand marking area respectively according to the second interaction information; When the inspection valve mark area and the hand mark area at least partially overlap: performing gesture input through the gesture input unit and updating the second real-time image; The processor obtains a gesture image according to the updated second real-time image; the processor calls the gesture instruction from the memory, and obtains the control signal according to the gesture image and the gesture instruction.

10. The maintenance method according to claim 8, characterized in that: The steps of obtaining the control signal are: When the control requirement is a gesture input: based on the control requirement, performing gesture input through the gesture input unit, and using the camera to photograph the gesture input unit to obtain a second real-time image and transmit the second real-time image to the processor; The processor updates the first interaction information according to the second real-time image to obtain the second interaction information, and the second interaction information is displayed through the display unit; The processor obtains a gesture image according to the second real-time image; The processor calls the gesture instruction from the memory and obtains a preparation signal according to the gesture image and the gesture instruction; The processor obtains the inspection valve marking area and the hand marking area respectively according to the second interaction information; When the inspection valve mark area and the hand mark area at least partially overlap: the processor obtains the control signal according to the preparation signal.

Images