AI edge calculation method and system for machine vision

Abstract

The invention relates to an AI edge calculation method and system for machine vision. The AI edge calculation system comprises a plurality of edge computers, an AI control terminal and a plurality of vision acquisition ends, the visual acquisition end comprises a camera and a shell, an insulating tube penetrates through one end of the shell, an inner tube penetrates through the insulating tube, and the end part of one end, located in the shell, of the insulating tube is closed; the end, located in the shell, of the insulating tube is sleeved with a magnetically-attracted mounting sleeve for mounting and fixing the camera, the mounting sleeve can axially rotate around the insulating tube, the inner tube is sleeved with an annular piston, and a magnet assembly for magnetically attracting the mounting sleeve is arranged in the annular piston; a one-way air inlet valve is arranged on the partial surface of the insulating tube in the shell; a detection unit for detecting gas components and pressure is arranged at an outlet at one end of the insulating tube far away from the shell; the safety performance can be greatly improved, the obtained video data and detection data are firstly processed by the edge computer and then sent to the AI control terminal for global analysis, and the data processing pressure can be greatly reduced.

Description

Technical Field

[0001] The present invention relates to the field of edge computers and machine vision technologies, and more specifically, to an AI edge computing method for machine vision. Background Art

[0002] Machine vision is a rapidly developing branch of artificial intelligence. Machine vision products (i.e., image capture devices, which are divided into two types: CMOS and CCD) convert the captured target into an image signal, which is transmitted to a dedicated image processing system to obtain the target's morphological information. Based on pixel distribution, brightness, color and other information, it is converted into a digital signal. The image system performs various operations on these signals to extract the target's features, and then controls the operation of the equipment on site based on the judgment results. In some scenarios with high concentrations of flammable gases and flammable dust (such as oil depots), the image acquisition process requires additional explosion-proof design, and the existing risks need to be quickly and intelligently processed. The existing machine vision methods are not capable of this task and require more manual intervention. At the same time, the prevention effect is not ideal, and it is impossible to conduct a global safety assessment. A safer and more efficient AI edge computing method is needed for this scenario. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an AI edge computing method for machine vision and an AI edge computing system for machine vision in response to the above-mentioned defects of the prior art.

[0004] The technical solution adopted by the present invention to solve its technical problem is: An AI edge computing system for machine vision is constructed, which includes multiple edge computers, AI control terminals and multiple visual acquisition terminals; the visual acquisition terminal includes a camera and a strip-shaped shell, one end of the shell is sealed and fixedly penetrated by an insulating tube, a rotatable inner tube is penetrated in the insulating tube, and the end of the insulating tube located in the shell is closed; the end of the insulating tube located in the shell is sleeved with a magnetic mounting sleeve for mounting and fixing the camera, the mounting sleeve can rotate around the axial direction of the insulating tube, an annular piston is sleeved on the inner tube, and a magnet assembly for magnetically attracting the mounting sleeve is provided in the annular piston; a transparent protective cover is embedded in the shell; one end of the inner tube is connected to an exhaust unit for extracting inert gas from it, a pulling unit for pulling the inner tube and a rotating unit for driving the inner tube to rotate, so The other end of the inner tube is rotatably connected to a switching plug; the switching plug is movably arranged at the end of the insulating tube, and the switching plug is provided with a switching channel connected to the inner hole of the inner tube. The switching plug is pulled by the inner tube and has a first state and a second state. In the first state, the switching channel connects the inner hole of the insulating tube and the inner hole of the inner tube, and in the second state, the switching channel connects the inner hole of the insulating tube and the internal space of the outer shell. A one-way air intake valve is provided on the surface of the insulating tube located inside the outer shell, and a detection unit for detecting gas composition and pressure is provided at the outlet of the end of the insulating tube away from the outer shell; the edge computer receives the video data of the camera and the detection data of the detection unit, generates a safety status index after corresponding data processing, and uploads it to the AI ​​control terminal.

[0005] The AI ​​edge computing system for machine vision described in the present invention, wherein the exhaust and exhaust unit includes a mounting plate, on which an inert gas inflation module and an exhaust module that are both connected to the inner tube are provided.

[0006] The AI ​​edge computing system for machine vision described in the present invention is characterized in that the inner tube is rotatably connected to the mounting plate; the pulling unit includes a cylinder, and the movable end of the cylinder is fixedly connected to the mounting plate; the rotating unit includes a servo motor, which is installed on the mounting plate, and the movable end of the servo motor is provided with a spline, and the coaxial sleeve on the inner tube is provided with a spline sleeve that cooperates with the spline.

[0007] In the AI ​​edge computing system for machine vision of the present invention, the switching channel includes a first channel arranged along the length direction of the switching plug, and the switching plug is provided with a second channel connected to the first channel and a third channel connected to the first channel in a radial direction; In the first state, the inner hole of the insulating tube and the inner hole of the inner tube are connected through the first hole and the second hole, and the third hole is blocked and closed; In the second state, the first channel and the third channel communicate with the inner hole of the insulating tube and the inner space of the shell, and the second channel is blocked and closed.

[0008] The AI ​​edge computing system for machine vision described in the present invention, wherein the magnet assembly includes a plurality of strong magnets uniformly distributed circumferentially on the annular piston, and the inner wall of the mounting sleeve is provided with a plurality of iron pieces corresponding one-to-one to the strong magnets.

[0009] The AI ​​edge computing system for machine vision described in the present invention, wherein the one-way air intake valve and the switching plug are respectively located at two end positions of the shell.

[0010] The AI ​​edge computing system for machine vision described in the present invention is characterized in that an annular detection chamber is provided at the end of the insulating tube, and a sealed bearing assembly connected to the inner tube is provided at the center of the detection chamber; the sealed bearing assembly includes a rotating sealed bearing and a linear sealed bearing, the linear sealed bearing is inserted into the rotating sealed bearing, and the outer ring of the linear sealed bearing is fixedly connected to the inner ring of the rotating sealed bearing, and the inner tube is inserted into the linear sealed bearing; the detection unit includes a gas sensor for detecting gas components and a pressure sensor located in the detection chamber; the detection chamber is also provided with an exhaust unit.

[0011] An AI edge computing method for machine vision is applied to the AI ​​edge computing system for machine vision as described above, wherein the method comprises the steps of: According to the set inspection procedure, internal gas detection is carried out when the set time arrives: The pulling unit drives the inner tube to move, thereby driving the switching plug to the second state, and the switching channel connects the inner hole of the insulating tube and the inner space of the outer shell; The exhaust unit is operated to fill the inner tube with inert gas, and the inert gas enters the inner space of the shell through the switching channel, and squeezes the gas in the inner space of the shell into the inner hole of the insulating tube through the one-way air inlet valve; The detection unit detects the gas composition and pressure in the insulating tube. If the inert gas content and pressure in the gas composition are both within the corresponding set normal threshold range, it is determined that there is no inert gas leakage; otherwise, it is determined that there is an inert gas leakage; The edge computer receives the video data from the camera and the detection data from the detection unit, processes the data accordingly, generates a safety status index, and uploads it to the AI ​​control terminal; The AI ​​control terminal evaluates the overall security performance based on the security status index of multiple edge computers.

[0012] The AI ​​edge computing method for machine vision according to the present invention comprises the following steps: Receive position adjustment instructions sent from the outside and adjust the position of the camera according to the adjustment instructions: The pulling unit drives the inner tube to move, thereby driving the switching plug to be in the first state, and the switching channel connects the inner hole of the insulating tube and the inner hole of the inner tube; The operation of the gas extraction and discharge unit fills or extracts inert gas into the inner tube, and then changes the position of the annular piston by relying on the gas pressure; The annular piston drives the mounting sleeve to move along the insulating tube based on the magnetic attraction, thereby driving the camera to move.

[0013] The AI ​​edge computing method for machine vision according to the present invention comprises the following steps: Receive rotation angle adjustment instructions sent from the outside and adjust the rotation angle of the camera according to the adjustment instructions: The rotating unit drives the inner tube to rotate, thereby driving the annular piston to rotate. The annular piston drives the mounting sleeve to rotate around the insulating tube based on the magnetic attraction.

[0014] The beneficial effects of the present invention are as follows: according to the set inspection procedure, internal gas detection is performed when the set time arrives: the pulling unit drives the inner tube to move, and then drives the switching plug to the second state, and the switching channel connects the inner hole of the insulating tube and the internal space of the outer shell; the exhaust unit operates to fill the inner tube with inert gas, and the filled inert gas enters the internal space of the outer shell through the switching channel, and squeezes the gas in the internal space of the outer shell into the inner hole of the insulating tube through the one-way air inlet valve; the detection unit detects the gas composition and pressure in the insulating tube, if the inert gas content and pressure in the gas composition are within the corresponding set normal threshold range, it is determined that there is no inert gas leakage, otherwise it is determined that there is an inert gas leakage; the edge computer receives the video data of the camera and the detection data of the detection unit, generates a safety status index after corresponding data processing, and uploads it to the AI ​​control terminal; the AI ​​control terminal evaluates the overall safety performance according to the safety status indexes of multiple edge computers; The application of the method and approach of this application can not only solve the safety protection problem of visual acquisition, but also has the function of adjusting the position and angle of the camera, so that the camera can complete monitoring cruise in an explosion-proof state, and the control components of all actions are set at the far end away from the outer shell, and the transmission of actions is completed with inert gas as the carrier, which can greatly improve the safety performance. The acquired video data and detection data are first processed by the edge computer and then sent to the AI ​​control terminal for global analysis, which can greatly reduce the data processing pressure on the control end. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be further described below with reference to the accompanying drawings and embodiments. The drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive efforts. Figure 1 This is a block diagram of the principle of an AI edge computing system for machine vision according to a preferred embodiment of the present invention; Figure 2 This is a structural diagram of the visual acquisition end of the AI ​​edge computing system for machine vision in a preferred embodiment of the present invention; Figure 3 This is a cross-sectional view of the visual acquisition end of the AI ​​edge computing system for machine vision in a preferred embodiment of the present invention; Figure 4 This is a cross-sectional view of an end portion of an insulating tube of an AI edge computing system for machine vision according to a preferred embodiment of the present invention; Figure 5 This is a schematic diagram of the exterior of an insulating tube of an AI edge computing system for machine vision according to a preferred embodiment of the present invention; Figure 6 This is a flow chart of the AI ​​edge computing method for machine vision in a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0016] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the following will be a clear and complete description of the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work shall fall within the scope of protection of the present invention.

[0017] The AI ​​edge computing system for machine vision in a preferred embodiment of the present invention is as follows: Figure 1 See also Figure 2-Figure 5, including multiple edge computers 10, AI control terminals 11 and multiple visual acquisition terminals 12; the visual acquisition terminal 12 includes a camera 1 and a strip-shaped shell 2 (preferably an explosion-proof shell), one end of the shell 2 is sealed and fixed with an insulating tube 3, a rotatable inner tube 4 is inserted into the insulating tube 3, and the end of the insulating tube 3 located in the shell 2 is closed; one end of the insulating tube 3 located in the shell 2 is provided with a magnetic mounting sleeve 5 for mounting and fixing the camera 1, the mounting sleeve 5 can rotate axially around the insulating tube 3, an annular piston 6 is provided on the inner tube 4, and a magnet assembly 7 of the magnetic mounting sleeve 5 is provided in the annular piston 6; a transparent shield 20 for shooting is embedded in the shell 2; one end of the inner tube 4 is connected to a gas extraction unit for extracting inert gas from it, a pulling unit 41 for pulling the inner tube, and a rotating unit 42 for driving the inner tube to rotate, and the inner tube 4 The other end is rotatably connected to a switching plug 43; the switching plug 43 is movably arranged at the end of the insulating tube 3, and is provided with a switching channel 430 connected to the inner hole of the inner tube 4. The switching plug 43 is pulled and moved by the inner tube 4 and has a first state and a second state. In the first state, the switching channel 430 connects the inner hole of the insulating tube 3 and the inner hole of the inner tube 4, and in the second state, the switching channel 430 connects the inner hole of the insulating tube 3 and the internal space of the shell 2. A one-way air intake valve 30 is provided on the surface of the insulating tube 3 located inside the shell 2, and a detection unit 31 for detecting gas composition and pressure is provided at the outlet of the end of the insulating tube 3 away from the shell 2; the edge computer 10 receives the video data of the camera 1 and the detection data of the detection unit 31, generates a safety status index after corresponding data processing, and uploads it to the AI ​​control terminal 11; According to the set inspection procedure, internal gas detection is performed when the set time arrives: the pulling unit 41 drives the inner tube 4 to move, and then drives the switching plug 43 to the second state, and the switching channel 430 connects the inner hole of the insulating tube and the internal space of the outer shell; the exhaust unit runs to fill the inner tube 4 with inert gas, and the filled inert gas enters the internal space of the outer shell 2 through the switching channel 430, and squeezes the gas in the internal space of the outer shell 2 into the inner hole of the insulating tube 3 through the one-way air inlet valve 30; the detection unit 31 detects the gas composition and pressure in the insulating tube 3. If the inert gas content and pressure in the gas composition are both within the corresponding set normal threshold range, it is determined that there is no inert gas leakage, otherwise it is determined that there is an inert gas leakage; the edge computer 10 receives the video data of the camera 1 and the detection data of the detection unit 31, generates a safety status index after corresponding data processing, and uploads it to the AI ​​control terminal 11; the AI ​​control terminal 11 evaluates the overall safety performance based on the safety status indexes of multiple edge computers 10; The application of the method and approach of this application can not only solve the safety protection problem of visual acquisition, but also has the function of adjusting the position and angle of the camera, so that the camera can complete monitoring and cruising in an explosion-proof state, and the control components of all actions are set at the far end away from the outer shell (can be extended to a relatively safe area by relying on the insulating tube 3 and the inner tube 4), and the transmission of actions is completed with inert gas as the carrier, which can greatly improve the safety performance. The acquired video data and detection data are first processed by the edge computer and then sent to the AI ​​control terminal for global analysis, which can greatly reduce the data processing pressure on the control end.

[0018] Preferably, the exhaust and exhaust unit includes a mounting plate 400, on which an inert gas inflation module 401 and an exhaust module 402 that are both connected to the inner tube are provided; the inner tube 4 is rotatably connected to the mounting plate 400 (two limit blocks can be set to limit the rotation angle); the pulling unit 41 includes a cylinder, and the movable end of the cylinder is fixedly connected to the mounting plate 400; the rotating unit 42 includes a servo motor 420, which is mounted on the mounting plate 400, and the movable end of the servo motor 420 is provided with a spline 421, and the coaxial sleeve on the inner tube 4 is provided with a spline sleeve 422 that cooperates with the spline; adopting this structural layout design, the overall volume can be made smaller, the function is rich and the structure is also very compact.

[0019] Preferably, the switching channel 430 includes a first channel 4300 arranged along the length direction of the switching plug 43, and a second channel 4301 communicating with the first channel 4300 and a third channel 4302 communicating with the first channel 4300 are arranged on the switching plug in the radial direction; In the first state, the inner hole of the insulating tube 3 and the inner hole of the inner tube 4 are connected through the first hole 4300 and the second hole 4301, and the third hole 4302 is blocked and closed; In the second state, the first hole 4300 and the third hole 4302 communicate with the inner hole of the insulating tube 3 and the inner space of the shell 2, and the second hole 4301 is blocked and closed. The structure is simple, the switching reliability is good, the operation is very convenient and the cost is low.

[0020] Preferably, the magnet assembly 7 includes a plurality of strong magnets 70 uniformly distributed along the circumferential direction on the annular piston 6 , and the inner wall of the mounting sleeve 5 is provided with a plurality of iron pieces 50 corresponding one-to-one to the strong magnets 70 .

[0021] Preferably, the one-way air inlet valve 30 and the switching plug 43 are respectively located at two ends of the housing 2 to ensure the detection effect of the inert gas leakage detection.

[0022] Preferably, an annular detection chamber 8 is provided at the end of the insulating tube 3, and a sealed bearing assembly 80 connected to the inner tube 4 is provided at the center of the detection chamber 8; the sealed bearing assembly 80 includes a rotating sealed bearing and a linear sealed bearing, the linear sealed bearing is inserted into the rotating sealed bearing, and the outer ring of the linear sealed bearing is fixedly connected to the inner ring of the rotating sealed bearing, and the inner tube is inserted into the linear sealed bearing; the detection unit 31 includes a gas sensor 310 for detecting gas composition and a pressure sensor 311 located in the detection chamber 8; the structure is reasonable and compact, which is beneficial to the installation; Preferably, an exhaust unit 81 is also provided on the detection chamber 8; during the inert gas leakage detection, the exhaust unit should be in a closed state to detect the air pressure and gas composition inside the insulating tube; when adjusting the position of the camera 1, the exhaust unit 81 should be opened to exhaust appropriately to avoid the formation of negative pressure in the insulating tube, which would interfere with the smooth adjustment.

[0023] An AI edge computing method for machine vision is applied to the AI ​​edge computing system for machine vision as described above, such as Figure 6 As shown, the method includes the steps of: According to the set inspection procedure, internal gas detection is carried out when the set time arrives: S01: The pulling unit drives the inner tube to move, thereby driving the switching plug to the second state, and the switching channel connects the inner hole of the insulating tube and the inner space of the outer shell; S02: The exhaust unit operates to fill the inner tube with inert gas, and the inert gas enters the inner space of the shell through the switching channel, and squeezes the gas in the inner space of the shell into the inner hole of the insulating tube through the one-way air inlet valve; S03: The detection unit detects the gas composition and pressure in the insulating tube. If the inert gas content and pressure in the gas composition are both within the corresponding set normal threshold range, it is determined that there is no inert gas leakage; otherwise, it is determined that there is an inert gas leakage; S04: The edge computer receives the video data from the camera and the detection data from the detection unit, processes the data accordingly, generates a safety status index, and uploads it to the AI ​​control terminal; The safety status index can be customized with a mapping table that maps video data to dangerous scenarios and detection data to leakage status, and generates a safety status index by combining dangerous scenarios and leakage status. S05: The AI ​​control terminal evaluates the overall security performance based on the security status index of multiple edge computers.

[0024] The assessment can be performed based on the weight of the edge computer's location and combined with the security status index to obtain the security performance level of each edge computer's corresponding location. Edge computers that are below the set security threshold will be monitored or maintained in a timely manner.

[0025] The method further comprises the steps of: Receive position adjustment instructions sent from the outside and adjust the position of the camera according to the adjustment instructions: The pulling unit drives the inner tube to move, thereby driving the switching plug to be in the first state, and the switching channel connects the inner hole of the insulating tube and the inner hole of the inner tube; The operation of the gas extraction and discharge unit fills or extracts inert gas into the inner tube, and then changes the position of the annular piston by relying on the gas pressure; The annular piston drives the mounting sleeve to move along the insulating tube based on the magnetic attraction, thereby driving the camera to move; The method further comprises the steps of: Receive rotation angle adjustment instructions sent from the outside and adjust the rotation angle of the camera according to the adjustment instructions: The rotating unit drives the inner tube to rotate, thereby driving the annular piston to rotate. The annular piston drives the mounting sleeve to rotate around the insulating tube based on the magnetic attraction.

[0026] The application of the method and approach of this application can not only solve the safety protection problem of visual acquisition, but also has the function of adjusting the position and angle of the camera, so that the camera can complete monitoring cruise in an explosion-proof state, and the control components of all actions are set at the far end away from the outer shell, and the transmission of actions is completed with inert gas as the carrier, which can greatly improve the safety performance. The acquired video data and detection data are first processed by the edge computer and then sent to the AI ​​control terminal for global analysis, which can greatly reduce the data processing pressure on the control end.

[0027] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention.

Claims

1. An AI edge computing system for machine vision, characterized in that: It comprises a plurality of edge computers, an AI control terminal and a plurality of visual acquisition terminals; the visual acquisition terminal comprises a camera and a strip-shaped shell, one end of the shell is sealed and fixedly penetrated with an insulating tube, a rotatable inner tube is penetrated in the insulating tube, and the end of the insulating tube located in the shell is closed; one end of the insulating tube located in the shell is provided with a magnetic mounting sleeve for mounting and fixing the camera, the mounting sleeve can rotate around the axial direction of the insulating tube, an annular piston is provided on the inner tube, and a magnet assembly for magnetically attracting the mounting sleeve is provided in the annular piston; a transparent protective cover is embedded in the shell; one end of the inner tube is connected to an exhaust unit for extracting inert gas from it, a pulling unit for pulling the inner tube and a rotating unit for driving the inner tube to rotate, and the other end of the inner tube is rotatably connected There is a switching plug; the switching plug is movably arranged at the end of the insulating tube, and the switching plug is provided with a switching channel connected to the inner hole of the inner tube. The switching plug is pulled by the inner tube and has a first state and a second state. In the first state, the switching channel connects the inner hole of the insulating tube and the inner hole of the inner tube, and in the second state, the switching channel connects the inner hole of the insulating tube and the internal space of the outer shell. A one-way air intake valve is provided on the surface of the part of the insulating tube located inside the outer shell, and a detection unit for detecting gas composition and pressure is provided at the outlet of the end of the insulating tube away from the outer shell; the edge computer receives the video data of the camera and the detection data of the detection unit, generates a safety status index after corresponding data processing, and uploads it to the AI ​​control terminal.

2. The AI ​​edge computing system for machine vision according to claim 1, characterized in that The gas extraction and exhaust unit includes a mounting plate, on which an inert gas inflation module and a gas extraction module both in communication with the inner tube are arranged.

3. The AI ​​edge computing system for machine vision according to claim 2, characterized in that The inner tube is rotatably connected to the mounting plate; the pulling unit includes a cylinder, the movable end of which is fixedly connected to the mounting plate; the rotating unit includes a servo motor, which is mounted on the mounting plate, and the movable end of the servo motor is provided with a spline, and the coaxial sleeve on the inner tube is provided with a spline sleeve that cooperates with the spline.

4. The AI ​​edge computing system for machine vision according to claim 1, wherein: The switching channel includes a first channel arranged along the length direction of the switching plug, a second channel connected to the first channel and a third channel connected to the first channel arranged radially on the switching plug; In the first state, the inner hole of the insulating tube and the inner hole of the inner tube are connected through the first hole and the second hole, and the third hole is blocked and closed; In the second state, the first channel and the third channel communicate with the inner hole of the insulating tube and the inner space of the shell, and the second channel is blocked and closed.

5. The AI ​​edge computing system for machine vision according to claim 1, wherein: The magnet assembly includes a plurality of strong magnets uniformly distributed along the circumference of the annular piston, and the inner wall of the mounting sleeve is provided with a plurality of iron pieces corresponding to the strong magnets one by one.

6. The AI ​​edge computing system for machine vision according to claim 1, characterized in that The one-way air intake valve and the switching plug are respectively located at two end positions of the housing.

7. The AI ​​edge computing system for machine vision according to claim 1, characterized in that The end of the insulating tube is connected to a ring-shaped detection chamber, and a sealing bearing assembly connected to the inner tube is provided at the center of the detection chamber; the sealing bearing assembly includes a rotating sealing bearing and a linear sealing bearing, the linear sealing bearing is inserted into the rotating sealing bearing, and the outer ring of the linear sealing bearing is fixedly connected to the inner ring of the rotating sealing bearing, and the inner tube is inserted into the linear sealing bearing; the detection unit includes a gas sensor for detecting gas components and a pressure sensor located in the detection chamber; the detection chamber is also provided with an exhaust unit.

8. An AI edge computing method for machine vision, applied to the AI ​​edge computing system for machine vision according to any one of claims 1 to 7, characterized in that: The method comprises the steps of: According to the set inspection procedure, internal gas detection is carried out when the set time arrives: The pulling unit drives the inner tube to move, thereby driving the switching plug to the second state, and the switching channel connects the inner hole of the insulating tube and the inner space of the outer shell; The exhaust unit is operated to fill the inner tube with inert gas, and the inert gas enters the inner space of the shell through the switching channel, and squeezes the gas in the inner space of the shell into the inner hole of the insulating tube through the one-way air inlet valve; The detection unit detects the gas composition and pressure in the insulating tube. If the inert gas content and pressure in the gas composition are both within the corresponding set normal threshold range, it is determined that there is no inert gas leakage; otherwise, it is determined that there is an inert gas leakage; The edge computer receives the video data from the camera and the detection data from the detection unit, processes the data accordingly, generates a safety status index, and uploads it to the AI ​​control terminal; The AI ​​control terminal evaluates the overall security performance based on the security status index of multiple edge computers.

9. The AI ​​edge computing method for machine vision according to claim 8, characterized in that: The method comprises the steps of: Receive position adjustment instructions sent from the outside and adjust the position of the camera according to the adjustment instructions: The pulling unit drives the inner tube to move, thereby driving the switching plug to be in the first state, and the switching channel connects the inner hole of the insulating tube and the inner hole of the inner tube; The operation of the gas extraction and discharge unit fills or extracts inert gas into the inner tube, and then changes the position of the annular piston by relying on the gas pressure; The annular piston drives the mounting sleeve to move along the insulating tube based on the magnetic attraction, thereby driving the camera to move.

10. The AI ​​edge computing method for machine vision according to claim 8, characterized in that: The method comprises the steps of: Receive rotation angle adjustment instructions sent from the outside and adjust the rotation angle of the camera according to the adjustment instructions: The rotating unit drives the inner tube to rotate, thereby driving the annular piston to rotate. The annular piston drives the mounting sleeve to rotate around the insulating tube based on the magnetic attraction.

Images