Method and equipment for monitoring insertion depth of sampling probe in environment-friendly tail gas detection process

Abstract

The invention is applicable to the technical field of tail gas detection, and particularly relates to a sampling probe insertion depth monitoring method and equipment in an environment-friendly tail gas detection process. Wherein the activity space information comprises information reflecting the physical state of the internal space of the exhaust pipe of the detected automobile; obtaining a fixed point based on the activity space information; wherein the fixed point reflects the fixed position of the sampling probe in the exhaust pipe in the tail gas detection process; and fixing the sampling probe based on the fixing point. According to the sampling probe insertion depth monitoring method and equipment in the environment-friendly tail gas detection process provided by the embodiment of the invention, the problem that the accuracy of a detection result is influenced due to insufficient sampling concentration caused by insufficient insertion depth of a sampling probe of a tail gas detection device can be solved; and carbon deposition generated in the exhaust pipe has an adverse effect on a detection result.

Description

Technical Field

[0001] This application belongs to the field of exhaust gas detection technology, and in particular relates to a method and equipment for monitoring the insertion depth of sampling probes during environmental exhaust gas detection. Background Technology

[0002] With economic development and rapid urbanization, the number of motor vehicles has increased rapidly, making vehicle exhaust emissions one of the main sources of urban air pollution. To control the pollution caused by vehicle exhaust emissions, regular exhaust emission testing can ensure vehicles meet standards, accelerate the replacement of older vehicles, thereby reducing vehicle emissions and improving air quality.

[0003] However, in traditional exhaust gas testing, the sampling probe of the exhaust gas testing device is inserted too deeply and too close to the exhaust port, resulting in diluted exhaust gas and insufficient sample concentration, thus affecting the accuracy of the test results. Furthermore, carbon deposits may form on the vehicle's exhaust pipe over time, further impacting the accuracy of the test results. Summary of the Invention

[0004] This application provides a method and device for monitoring the insertion depth of a sampling probe during environmental exhaust gas detection, which can solve the problem that insufficient insertion depth of the sampling probe in the exhaust gas detection device or carbon deposits in the exhaust pipe can adversely affect the accuracy of the detection results.

[0005] In a first aspect, embodiments of this application provide a method for monitoring the insertion depth of a sampling probe during environmental exhaust gas detection, including:

[0006] Acquire activity space information; wherein, the activity space information includes information reflecting the physical state of the internal space of the exhaust pipe of the vehicle being tested;

[0007] A fixed point is obtained based on the activity space information; wherein, the fixed point reflects the fixed position of the sampling probe in the exhaust pipe during the exhaust gas detection process;

[0008] The sampling probe is fixed based on the fixed point.

[0009] The technical solutions described in this application embodiment have at least the following technical effects:

[0010] The sampling probe insertion depth monitoring method provided in this application for environmental exhaust gas testing first acquires the movable space information reflecting the internal physical state of the exhaust pipe of the vehicle being tested, thus clarifying the movable range of the sampling probe and improving the accuracy of the analysis method. Then, based on the movable space information, a fixed point reflecting the fixed position of the sampling probe in the exhaust pipe during exhaust gas testing is obtained, ensuring that insufficient insertion depth does not lead to insufficient sampling concentration or that carbon deposits in the vehicle's exhaust pipe affect the accuracy of the test results. Finally, the sampling probe is fixed at the fixed point, ensuring that it can be accurately fixed at a preset position within the exhaust pipe, thus ensuring the accuracy and reliability of the test results.

[0011] In one possible implementation of the first aspect, prior to acquiring the activity space information, the sampling probe insertion depth monitoring method during the environmental exhaust gas detection process further includes:

[0012] The cleaning device is controlled to clean the interior of the exhaust pipe of the vehicle being tested, and the cleaning depth is not less than p millimeters extending into the interior of the exhaust pipe from the position of the three-way catalytic converter or the tail of the exhaust pipe; wherein p ≥ 600.

[0013] In one possible implementation of the first aspect, obtaining the activity space information includes:

[0014] Obtain an exhaust pipe model; wherein the exhaust pipe model reflects the internal space of the exhaust pipe;

[0015] Acquire inner wall image information; wherein, the inner wall image information reflects the inner wall image of the exhaust pipe;

[0016] The exhaust pipe model and the inner wall image information are confirmed as the activity space information.

[0017] In one possible implementation of the first aspect, obtaining the exhaust pipe model includes:

[0018] A first control command is sent to the mobile device, and a second control command is sent to the scanning device simultaneously. The first control command instructs the mobile device to move the scanning device, image acquisition device, and sampling probe from the insertion point of the exhaust pipe towards the end of the exhaust pipe furthest from the exhaust outlet by *i* millimeters, and then stop moving. During the movement, the movement is paused for 5 seconds after every *j* millimeters of movement. *i* is a positive integer, *i* ≥ 600, and *j* is a positive integer, *j* ≥ 50. The scanning device is capable of scanning the internal structure of the exhaust pipe, and the image acquisition device is capable of acquiring an image of the inner wall of the exhaust pipe. The second control command instructs the scanning device to scan the exhaust pipe.

[0019] The system receives scanning data sent by the scanning device and obtains the exhaust pipe model based on the scanning data; wherein the exhaust pipe model includes a three-dimensional model reflecting the internal structure of the exhaust pipe, a starting position, and an ending position, the starting position being the position of the sampling probe inside the exhaust pipe when the second control command is sent, and the ending position being the position of the sampling probe inside the exhaust pipe after the moving device moves i millimeters.

[0020] In one possible implementation of the first aspect, acquiring the inner wall image information includes:

[0021] When sending the first control command, a third control command is simultaneously sent to the image acquisition device; wherein, the third control command is used to instruct the image acquisition device to take pictures of the inner wall of the exhaust pipe when the mobile device stops moving in order to obtain multiple segmented images, wherein the segmented images are the images acquired by the image acquisition device each time the mobile device stops moving.

[0022] The image acquisition device receives all the segmented images and stitches them together in the order of acquisition time to obtain the inner wall image information. The inner wall image information includes a planar image reflecting the structure of the inner wall of the exhaust pipe, as well as a starting end and a ending end. The starting end is the end of the planar image that is closer to the tail of the exhaust pipe, and the ending end is the end of the planar image that is farther away from the tail of the exhaust pipe.

[0023] In one possible implementation of the first aspect, obtaining the fixed point based on the activity space information includes:

[0024] The inner wall plane information is obtained by unfolding the exhaust pipe model along its length; wherein, the unfolding operation is an operation that can transform the exhaust pipe model from a pipe model into a planar model, and the inner wall plane information includes a planar model reflecting the inner wall structure of the exhaust pipe, as well as a starting point and an ending point, wherein the starting point is the vertical projection of the starting position on the planar model, and the ending point is the vertical projection of the ending position on the planar model.

[0025] The planar model is input into a first defect recognition model to obtain a first defect image; wherein, the first defect recognition model is a data model obtained by machine learning, and the first defect image includes the planar model and at least one first defect information marked on the planar model, the first defect information including a first defect range obtained by the first defect recognition model, a weight value corresponding to the first defect range, a first starting point corresponding to the starting point position, and a first ending point corresponding to the ending point position.

[0026] The planar image is input into a second defect recognition model to obtain a second defect image; wherein, the second defect recognition model is a data model obtained through machine learning, and the second defect image includes the planar image and at least one second defect information marked on the planar image, the second defect information including a second defect range obtained by the second defect recognition model, a weight value corresponding to the second defect range, a second starting point corresponding to the starting point position, and a second ending point corresponding to the ending point position;

[0027] The fixed point is obtained based on the first defect image and the second defect image.

[0028] In one possible implementation of the first aspect, obtaining the fixed point based on the first defect image and the second defect image includes:

[0029] An analysis environment is established based on the first defective image and the second defective image; wherein, the analysis environment includes coordinate axes on the same plane, the first defective image and the second defective image, the scale unit of the coordinate axes is millimeters, the scale coordinate value of the origin of the coordinate axes is equal to the scale coordinate value of the first starting point of the first defective image and the second starting point of the second defective image, and the extension direction of the coordinate axes is consistent with and parallel to the extension direction from the first starting point to the first ending point and the extension direction from the second starting point to the second ending point;

[0030] The analysis range is obtained based on the coordinate axis, wherein the analysis range is the range formed by extending a line perpendicular to the coordinate axis with a base length of k mm and the two endpoints perpendicular to the coordinate axis and in the same plane as the first defect image and the second defect image, where k is a positive integer and k≥10;

[0031] The fixed point is obtained based on the analysis environment and analysis range.

[0032] In one possible implementation of the first aspect, obtaining the fixed point based on the analysis environment and analysis scope includes:

[0033] The left endpoint of the analysis range is set to 400 mm, and the right endpoint of the analysis range is set to 400+k mm; wherein, the left endpoint is the endpoint of the bottom edge of the analysis range that is closest to the origin of the coordinate axis, and the right endpoint is the endpoint of the bottom edge of the analysis range that is furthest from the origin of the coordinate axis.

[0034] Step a: Determine whether the perpendicular line drawn from the left endpoint and the right endpoint to the coordinate axis, which is in the same plane as the first defect image and the second defect image, contacts the first defect range of the first defect information in the first defect image or the second defect range of the second defect information in the second defect image in the analysis environment;

[0035] If the vertical line contacts the first defect range of the first defect information in the first defect image or the second defect range of the second defect information in the second defect image, then the weight of the portion of the first defect range or the second defect range that contacts the vertical line and is located within the analysis range is calculated separately to obtain the segmentation weight. The segmentation weight is then added to the corresponding weight values ​​of the first defect range and the second defect range that are located within the analysis range and do not contact the vertical line to obtain the total weight value.

[0036] If the vertical line does not contact the first defect range of the first defect information in the first defect image and the second defect range of the second defect information in the second defect image, then the weight values ​​corresponding to the first defect range and the second defect range included in the analysis range are added together to obtain the total weight value;

[0037] Step b: Add the calculated total weight value to the weight table; wherein the weight table includes the total weight value and the scale values ​​of the left and right endpoints of the analysis range corresponding to the total weight value;

[0038] Step c: Determine whether the scale value of the right endpoint of the analysis range is equal to the scale value of the first endpoint of the first defect image or the scale value of the second endpoint of the second defect image;

[0039] If the scale value of the right endpoint is equal to the scale value of the first endpoint of the first defective image or the scale value of the second endpoint of the second defective image, then the fixed point is obtained based on the weight table.

[0040] If the scale value of the right endpoint is not equal to the scale value of the first endpoint of the first defective image and the scale value of the second endpoint of the second defective image, then add m to the scale values ​​of the left endpoint and the right endpoint and repeat steps a, b and c; where m is a positive integer and m≥1.

[0041] In one possible implementation of the first aspect, obtaining the fixed point based on the weight table includes:

[0042] By comparing multiple total weight values ​​in the weight table, the minimum weight value is obtained; wherein, the minimum weight value is the total weight value with the smallest value among multiple total weight values;

[0043] Add the scale values ​​of the left and right endpoints of the analysis range corresponding to the minimum weight value, and then divide by 2 to obtain a fixed scale value.

[0044] The position inside the exhaust pipe reflected by the fixed scale value is identified as the fixed point.

[0045] In one possible implementation of the first aspect, fixing the sampling probe based on the fixed point includes:

[0046] The moving device is controlled to move the sampling probe according to the fixed scale value reflected by the fixed point;

[0047] After the moving device moves to the distance reflected by the fixed scale value, the fixing device is controlled to fix the sampling probe in the center of the exhaust pipe and prevent it from contacting the inner wall of the exhaust pipe.

[0048] Secondly, embodiments of this application provide a sampling probe insertion depth monitoring system for environmental exhaust gas detection, including:

[0049] An acquisition unit is used to acquire activity space information; wherein, the activity space information includes information reflecting the physical state of the internal space of the exhaust pipe of the vehicle being tested;

[0050] An analysis unit is used to obtain a fixed point based on the activity space information; wherein the fixed point reflects the fixed position of the sampling probe in the exhaust pipe during the exhaust gas detection process;

[0051] A control unit is used to fix the sampling probe based on the fixed point.

[0052] Thirdly, embodiments of this application provide a sampling probe insertion depth monitoring device for environmental exhaust gas detection, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method described in any one of the first aspects above.

[0053] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any one of the first aspects above.

[0054] Fifthly, embodiments of this application provide a computer program product that, when running on a sampling probe insertion depth monitoring device during environmental exhaust gas detection, causes the sampling probe insertion depth monitoring device to execute the sampling probe insertion depth monitoring method described in any of the first aspects above.

[0055] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a flowchart illustrating a method for monitoring the insertion depth of a sampling probe during environmental exhaust gas detection, provided in an embodiment of this application.

[0058] Figure 2 This is a flowchart illustrating step S100 in the environmental exhaust gas detection method for monitoring the insertion depth of a sampling probe according to an embodiment of this application.

[0059] Figure 3 This is a flowchart illustrating step S110 in the environmental exhaust gas detection method for monitoring the insertion depth of a sampling probe according to an embodiment of this application.

[0060] Figure 4 This is a flowchart illustrating step S120 of the sampling probe insertion depth monitoring method in the environmental exhaust gas detection process provided in an embodiment of this application.

[0061] Figure 5 This is a flowchart illustrating step S200 in the environmental exhaust gas detection method for monitoring the insertion depth of a sampling probe according to an embodiment of this application.

[0062] Figure 6 This is a flowchart illustrating step S240 in the environmental exhaust gas detection method for monitoring the insertion depth of a sampling probe according to an embodiment of this application.

[0063] Figure 7 This is a flowchart illustrating step S243 in the environmental exhaust gas detection method for monitoring the insertion depth of a sampling probe according to an embodiment of this application.

[0064] Figure 8This is a flowchart illustrating step S2436 in the sampling probe insertion depth monitoring method for environmental exhaust gas detection provided in an embodiment of this application.

[0065] Figure 9 This is a flowchart illustrating step S300 in the environmental exhaust gas detection method for monitoring the insertion depth of a sampling probe according to an embodiment of this application.

[0066] Figure 10 This is a schematic diagram of the structure of a sampling probe insertion depth monitoring system provided in an embodiment of this application for environmental exhaust gas detection.

[0067] Figure 11 This is a schematic diagram of the structure of a sampling probe insertion depth monitoring device provided in an embodiment of this application for environmental exhaust gas detection. Detailed Implementation

[0068] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0069] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0070] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0071] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0072] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0073] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0074] In related technologies, insufficient insertion depth of the sampling probe in exhaust gas detection devices, resulting in excessive proximity to the exhaust port, leads to dilution of the exhaust gas and insufficient sample concentration, thus affecting the accuracy of the test results. Furthermore, carbon deposits may form on the vehicle's exhaust pipe due to prolonged operation, further complicating the accuracy of the test results.

[0075] To address the aforementioned issues, this application provides a method and device for monitoring the insertion depth of a sampling probe during exhaust gas testing. This method first acquires the movable space information reflecting the internal physical state of the exhaust pipe of the vehicle being tested, thus clarifying the movable range of the sampling probe and improving the accuracy of the analysis method. Then, based on the movable space information, a fixed point is determined reflecting the fixed position of the sampling probe in the exhaust pipe during exhaust gas testing. This ensures that insufficient insertion depth does not lead to insufficient sampling concentration, and that carbon deposits in the vehicle's exhaust pipe do not affect the accuracy of the test results. Finally, the sampling probe is fixed at the fixed point, ensuring that it is accurately fixed at a preset position within the exhaust pipe, thus ensuring the accuracy and reliability of the test results.

[0076] The sampling probe insertion depth monitoring method provided in this application embodiment can be applied to the sampling probe insertion depth monitoring device during the environmental exhaust gas detection process. In this case, the sampling probe insertion depth monitoring device during the environmental exhaust gas detection process is the execution subject of the sampling probe insertion depth monitoring method provided in this application embodiment. This application embodiment does not impose any restrictions on the specific type of sampling probe insertion depth monitoring device during the environmental exhaust gas detection process.

[0077] For example, a sampling probe insertion depth monitoring device used in environmental exhaust gas detection may include a control device, a cleaning device, a moving device, a scanning device, an image acquisition device, and a fixing device. The scanning device, image acquisition device, and fixing device are detachably mounted on the moving device, and all three are located at the end of the moving device that is inserted into the exhaust pipe. The fixing device can be connected to or separated from the sampling probe via a snap-fit ​​connection. The control device is communicatively connected to the communication devices of the cleaning device, moving device, scanning device, image acquisition device, and fixing device. The cleaning device is used to remove dirt from the inner wall of the exhaust pipe; for example, it may be a high-pressure water spray device or an electrically driven rotating brush device, but is not limited to these. The moving device is a device capable of moving or individually moving the sampling probe, scanning device, image acquisition device, and fixing device; for example, it may be a telescopic device or an electrically driven slide, but is not limited to these. The scanning device is a device capable of scanning the inner wall structure of the exhaust pipe; for example, it may be an ultrasonic scanner, an X-ray scanner, but is not limited to these. An image acquisition device is a device capable of capturing images of the inner wall of an exhaust pipe. For example, the image acquisition device can be a digital camera or an analog camera, but is not limited to these. A fixing device is a device capable of fixing a sampling probe in a preset position. For example, the fixing device can include a telescopic fixing rod and a fixing ring, etc., and the fixing ring can be connected to or separated from the sampling probe by a snap-fit, but is not limited to these.

[0078] To better understand the sampling probe insertion depth monitoring method provided in the embodiments of this application for environmental exhaust gas detection, the specific implementation process of the sampling probe insertion depth monitoring method provided in the embodiments of this application will be described in the following exemplary manner.

[0079] Figure 1 This paper presents a schematic flowchart of a method for monitoring the insertion depth of a sampling probe during environmental exhaust gas detection, as provided in an embodiment of this application. The method includes:

[0080] S100, acquire activity space information; wherein, the activity space information includes information reflecting the physical state of the internal space of the exhaust pipe of the vehicle being tested.

[0081] It is understandable that acquiring information about the movement space of the exhaust pipe of the vehicle being inspected can clarify the range of motion of the sampling probe and provide a detailed view of the internal wall of the exhaust pipe for analysis, thereby improving the accuracy of the analysis method. For example, the methods for acquiring this movement space information could include scanning modeling or image processing modeling, but are not limited to these.

[0082] Optionally, in S100, before acquiring activity space information, the sampling probe insertion depth monitoring method during environmental exhaust gas detection also includes:

[0083] The control cleaning device cleans the inside of the exhaust pipe of the vehicle being tested, and the cleaning depth is not less than p millimeters extending into the exhaust pipe from the position of the three-way catalytic converter or the tail of the exhaust pipe; where p ≥ 600.

[0084] In one possible implementation, please refer to Figure 2 S100, Obtain activity space information, including:

[0085] S110, Obtain the exhaust pipe model; wherein, the exhaust pipe model reflects the internal space of the exhaust pipe.

[0086] It is understandable that obtaining an exhaust pipe model that reflects the internal space of the exhaust pipe can clarify the movable range of the sampling probe, providing a basis for subsequent steps. For example, the exhaust pipe model can be obtained through X-ray scanning or ultrasonic scanning, but is not limited to these methods.

[0087] In one possible implementation, please refer to Figure 3 S110, Obtain the exhaust pipe model, including:

[0088] S111, send a first control command to the mobile device and simultaneously send a second control command to the scanning device; wherein, the first control command is used to instruct the mobile device to drive the scanning device, image acquisition device and sampling probe to move i millimeters away from the exhaust outlet of the exhaust pipe, starting from the insertion point of the exhaust pipe, and then stop moving, and during the movement, stop moving for 5 seconds after moving j millimeters, i is a positive integer, i≥600, j is a positive integer, j≥50, the scanning device is a device capable of scanning the internal structure of the exhaust pipe, the image acquisition device is a device capable of acquiring an image of the inner wall of the exhaust pipe, and the second control command is used to instruct the scanning device to scan the exhaust pipe.

[0089] It is understood that a moving device is a device capable of moving or independently moving the sampling probe, scanning device, image acquisition device, and fixing device. For example, the moving device can be a telescopic device or an electric slide, but it is not limited to these. Making the moving device stop moving for 5 seconds after moving j millimeters ensures that the image acquisition device is in a stable state when capturing images of the inner wall of the exhaust pipe, avoiding blurry images and facilitating subsequent steps. Here, j is a positive integer, j≥50.

[0090] S112, receive the scanning data sent by the scanning device, and obtain the exhaust pipe model based on the scanning data; wherein, the exhaust pipe model includes a three-dimensional model reflecting the internal structure of the exhaust pipe, a starting position and an ending position, the starting position is the position of the sampling probe in the exhaust pipe when the second control command is sent, and the ending position is the position of the sampling probe in the exhaust pipe after the moving device moves i millimeters.

[0091] It is understood that a scanning device is a device capable of scanning the internal structure of an exhaust pipe. For example, a scanning device can be an ultrasonic scanner, an X-ray scanner, etc., but it is not limited to these. An exhaust pipe model reflecting the internal structure of the exhaust pipe, obtained based on the scanning data, can more easily determine the physical condition of the exhaust pipe's inner wall.

[0092] S120, acquire inner wall image information; wherein, the inner wall image information reflects the inner wall image of the exhaust pipe.

[0093] It is understandable that obtaining images of the inner wall of the exhaust pipe can more easily help determine its physical condition, providing a basis for subsequent steps. The methods for obtaining these images include acquiring pictures transmitted from a camera or analyzing video footage captured by the camera, but are not limited to these methods.

[0094] In one possible implementation, please refer to Figure 4 S120, acquire inner wall image information, including:

[0095] S121, while sending the first control command, a third control command is simultaneously sent to the image acquisition device; wherein, the third control command is used to instruct the image acquisition device to take pictures of the inner wall of the exhaust pipe when the moving device stops moving in order to obtain multiple segmented images, and the segmented images are the images acquired by the image acquisition device each time the moving device stops moving.

[0096] It is understood that an image acquisition device is a device capable of capturing images of the inner wall of an exhaust pipe. For example, the image acquisition device can be a digital camera or an analog camera, but is not limited to these. Instructing the image acquisition device to take pictures of the inner wall of the exhaust pipe when the moving device has stopped moving can result in clearer images and avoid situations such as blurry images or noise caused by taking pictures during movement, which are detrimental to subsequent analysis steps.

[0097] S122, receive all segmented images sent by the image acquisition device, and stitch all segmented images together in the order of acquisition time to obtain inner wall image information; wherein, the inner wall image information includes a planar image reflecting the structure of the inner wall of the exhaust pipe, as well as a starting end and a ending end, the starting end being the end in the planar image closer to the tail of the exhaust pipe, and the ending end being the end in the planar image farther away from the tail of the exhaust pipe.

[0098] It is understandable that stitching together all segmented images in chronological order of acquisition to obtain the inner wall image information allows for the analysis of the image reflecting the inner wall of the exhaust pipe as a whole, which is beneficial for subsequent steps. For example, the method for stitching segmented images could be the APAP method or the SPHP method, but it is not limited to these.

[0099] S130, the exhaust pipe model and inner wall image information are identified as activity space information.

[0100] It is understandable that identifying the exhaust pipe model and inner wall image information as activity space information can provide a basis for subsequent steps.

[0101] S200, the fixed point is obtained based on the activity space information; where the fixed point reflects the fixed position of the sampling probe in the exhaust pipe during the exhaust gas detection process.

[0102] It is understandable that the fixed point of the sampling probe in the exhaust pipe is obtained based on the activity space information, which is reflected in the fixed position of the sampling probe during the exhaust gas detection process. This ensures that the sampling probe will not have insufficient sampling concentration due to insufficient insertion depth, and that carbon deposits in the car's exhaust pipe will not affect the accuracy of the test results.

[0103] In one possible implementation, please refer to Figure 5 S200, based on the activity space information, obtains fixed points, including:

[0104] S210, after unfolding the exhaust pipe model along its length, the inner wall plane information is obtained; wherein, the unfolding operation is an operation that can transform the exhaust pipe model from a pipe model into a planar model, and the inner wall plane information includes a planar model reflecting the inner wall structure of the exhaust pipe, as well as a starting point and an ending point. The starting point is the vertical projection of the starting position on the planar model, and the ending point is the vertical projection of the ending position on the planar model.

[0105] It is understandable that unfolding the exhaust pipe model along its length to obtain information about the inner wall plane allows for a more intuitive analysis and assessment of the physical condition of the exhaust pipe's inner wall, which is beneficial for subsequent steps. For example, the unfolding operation could be based on a mesh-based face-changing approximation method or a rectangular segmentation and perpendicular line method, but it is not limited to these.

[0106] S220, the planar model is input into the first defect recognition model to obtain the first defect image; wherein, the first defect recognition model is a data model obtained by machine learning, the first defect image includes the planar model and at least one first defect information marked on the planar model, the first defect information includes the first defect range obtained by the first defect recognition model, the weight value corresponding to the first defect range, the first starting point corresponding to the starting point position, and the first ending point corresponding to the ending point position.

[0107] It is understood that the first defect recognition model is trained using machine learning with multiple sets of data. These sets of data include a first category and a second category. Each set of data in the first category includes: a model of the exhaust pipe inner wall containing at least one defect; the outline of the defect in the model, manually analyzed and identified; and the weight corresponding to the defect, calculated manually as the ratio of the defect's area to the model's area. Each set of data in the second category includes: an exhaust pipe inner wall model excluding defects; and a label manually indicating that the model does not contain defects. Obtaining the first defect image using the first defect recognition model is more accurate and efficient than manual judgment, thus improving processing efficiency.

[0108] S230, the planar image is input into the second defect recognition model to obtain the second defect image; wherein, the second defect recognition model is a data model obtained by machine learning, the second defect image includes the planar image and at least one second defect information marked on the planar image, the second defect information includes the second defect range obtained by the second defect recognition model, the weight value corresponding to the second defect range, the second starting point corresponding to the starting position, and the second ending point corresponding to the ending position.

[0109] It is understood that the second defect recognition model is trained using multiple sets of data through machine learning. These sets of data include a first category and a second category. Each set of data in the first category includes: an image of the exhaust pipe inner wall containing at least one defect, the outline of the defect in the image analyzed and identified manually, and a weight corresponding to the defect obtained by manually calculating the ratio of the defect's area to the area of ​​the model. Each set of data in the second category includes: an image of the exhaust pipe inner wall excluding defects and a label manually indicating that the image does not contain defects. The second defect recognition model provides a more accurate and efficient second defect image compared to manual judgment, thus improving processing efficiency.

[0110] S240, a fixed point is obtained based on the first defect image and the second defect image.

[0111] It is understandable that obtaining fixed points based on the first and second defect images can ensure that the sampling probe will not have insufficient sampling concentration due to insufficient insertion depth, and that carbon deposits in the car exhaust pipe will not affect the accuracy of the detection results.

[0112] In one possible implementation, please refer to Figure 6 S240, obtaining fixed points based on the first defect image and the second defect image, including:

[0113] S241, establish an analysis environment based on the first defect image and the second defect image; wherein, the analysis environment includes coordinate axes on the same plane, the first defect image and the second defect image, the scale unit of the coordinate axes is millimeters, the scale coordinate value of the origin of the coordinate axes is equal to the scale coordinate value of the first starting point of the first defect image and the second starting point of the second defect image, and the extension direction of the coordinate axes is consistent with and parallel to the extension direction from the first starting point to the first ending point and the extension direction from the second starting point to the second ending point.

[0114] It is understandable that making the scale coordinate values ​​of the origin of the coordinate axis equal to the scale coordinate values ​​of the first starting point of the first defective image and the second starting point of the second defective image, and making the extension direction of the coordinate axis consistent with and parallel to the extension direction from the first starting point to the first ending point and the extension direction from the second starting point to the second ending point, can ensure that the content reflected by the first defective image and the second defective image corresponds within the closed interval reflected by any two scale values ​​of the coordinate axis, thus ensuring the reliability of the fixed point.

[0115] S242, the analysis range is obtained based on the coordinate axis, wherein the analysis range is the range formed by extending a perpendicular line with a base length of k mm on the coordinate axis and the two endpoints perpendicular to the coordinate axis, which is in the same plane as the first defect image and the second defect image, where k is a positive integer and k≥10.

[0116] It is understandable that obtaining the analysis range based on the coordinate axes allows for segmented analysis of the exhaust pipe, providing support for obtaining fixed points.

[0117] S243, a fixed point is obtained based on the analysis environment and analysis range.

[0118] It is understandable that determining the fixed point based on the analysis environment and analysis range can ensure that the sampling probe will not have insufficient sampling concentration due to insufficient insertion depth, and that carbon deposits in the car exhaust pipe will not affect the accuracy of the test results.

[0119] In one possible implementation, please refer to Figure 7 S243, Based on the analysis environment and analysis scope, fixed points are obtained, including:

[0120] S2431, set the scale value of the left end point of the analysis range to 400 mm, and set the scale value of the right end point of the analysis range to 400+k mm; where the left end point is the end point of the bottom edge of the analysis range that is closest to the origin of the coordinate axis, and the right end point is the end point of the bottom edge of the analysis range that is furthest from the origin of the coordinate axis.

[0121] It is understandable that setting the scale value of the left end of the analysis range to 400 mm can ensure that the insertion depth of the sampling probe is not less than 400 mm, and ensure that the sampling analysis process complies with the "Limits and Measurement Methods for Pollutant Emissions from Diesel Vehicles (Free Acceleration Method and Loaded Deceleration Method)".

[0122] S2432, Step a: Determine whether the perpendicular lines drawn from the left and right endpoints to the coordinate axes and in the same plane as the first defect image and the second defect image come into contact with the first defect range of the first defect information in the first defect image or the second defect range of the second defect information in the second defect image in the analysis environment.

[0123] It can be understood that determining whether a defect exists where a portion of the defect is located within the analysis range and a portion is located outside the analysis range is equivalent to determining whether a line drawn perpendicular to the coordinate axis from the left and right endpoints and in the same plane as the first defect image and the second defect image touches the first defect range of the first defect information in the first defect image or the second defect range of the second defect information in the second defect image in the analysis environment.

[0124] S2433, if the vertical line contacts the first defect range of the first defect information in the first defect image or the second defect range of the second defect information in the second defect image, then the weight of the portion of the first defect range or the second defect range that is in contact with the vertical line and located within the analysis range is calculated separately to obtain the segmentation weight, and the segmentation weight is added to the corresponding weight values ​​of the first defect range and the second defect range that are in the analysis range and are not in contact with the vertical line to obtain the total weight value.

[0125] It is understandable that the weight of the portion of the first or second defect range that is in contact with the vertical line and lies within the analysis range can be obtained by multiplying the ratio of the area within the analysis range to the total area of ​​defects in contact with the vertical line by the weight corresponding to that defect.

[0126] For example, suppose the defect that is in contact with the vertical line is a standard square with an area of ​​4, and the weight of the defect is 1. The vertical line divides the defect into two parts of equal size, and the area of ​​the defect within the analysis range is 2. Then the division weight of the defect is (2 / 4)*1 = 0.5.

[0127] Assuming the sum of the segmentation weights of defects that are in contact with the vertical line is 10, and the sum of the weights of defects that are not in contact with the vertical line is 20, then the total weight value = 10 + 20 = 30.

[0128] S2434, if the vertical line does not contact the first defect range of the first defect information in the first defect image and the second defect range of the second defect information in the second defect image, then the weight values ​​corresponding to the first defect range and the second defect range included in the analysis range are added together to obtain the total weight value.

[0129] It is understandable that adding the corresponding weight values ​​of the first and second defect ranges included in the analysis scope to obtain the total weight value can provide a basis for subsequent steps.

[0130] S2435, step b, add the calculated total weight value to the weight table; wherein, the weight table includes the total weight value and the scale values ​​of the left and right endpoints of the analysis range corresponding to the total weight value.

[0131] It's understandable that adding the calculated total weight value to the weight table can help analyze and determine the location of the fixed point.

[0132] S2436, step c, determine whether the scale value of the right endpoint of the analysis range is equal to the scale value of the first endpoint of the first defect image or the scale value of the second endpoint of the second defect image.

[0133] If the scale value of the right endpoint is equal to the scale value of the first endpoint of the first defective image or the scale value of the second endpoint of the second defective image, then a fixed point is obtained based on the weight table.

[0134] If the scale value of the right endpoint is not equal to the scale value of the first endpoint of the first defect image and the scale value of the second endpoint of the second defect image, then add m to the scale values ​​of the left and right endpoints and repeat steps a, b and c; where m is a positive integer and m≥1.

[0135] It can be understood that determining whether the scale value of the right endpoint of the analysis range is equal to the scale value of the first endpoint of the first defective image or the second endpoint of the second defective image means determining whether the analysis range has completely analyzed the first or second defective image. If the scale value of the right endpoint is not equal to the scale values ​​of the first endpoint of the first defective image or the second endpoint of the second defective image, it means that some defective images have not been analyzed. Adding 'm' to the scale value of the endpoint of the analysis range moves the analysis range towards the end of the image, ensuring that the image can be completely analyzed.

[0136] In one possible implementation, please refer to Figure 8 S2436, The fixed points are obtained based on the weight table, including:

[0137] S24361, compare multiple total weight values ​​in the weight table to obtain the minimum weight value; where the minimum weight value is the smallest total weight value among multiple total weight values.

[0138] It is understandable that by comparing and obtaining the minimum weight value, we can find the section of the exhaust pipe that has the least impact on the test results.

[0139] S24362, add the scale values ​​of the left and right endpoints of the analysis range corresponding to the minimum weight value, and then divide by 2 to obtain the fixed scale value.

[0140] It can be understood that the fixed scale value obtained by adding the scale values ​​of the left and right ends of the analysis range corresponding to the minimum weight value and dividing by 2 is used to determine the insertion depth of the sampling probe.

[0141] For example, assuming the scale value at the left end of the analysis range is 500 and the scale value at the right end of the analysis range is 510, then the fixed scale value = (500 + 510) / 2 = 505.

[0142] S24363, the position inside the exhaust pipe reflected by the fixed scale value is confirmed as a fixed point.

[0143] It is understandable that confirming the position inside the exhaust pipe reflected by the fixed scale value as a fixed point can minimize the adverse effects of carbon deposits or other defects inside the car's exhaust pipe on the test results.

[0144] S300, a fixed-point fixed sampling probe.

[0145] It is understandable that using a fixed-point sampling probe ensures that the sampling concentration will not be insufficient due to insufficient insertion depth, and that carbon deposits in the car exhaust pipe will not affect the accuracy of the test results.

[0146] In one possible implementation, please refer to Figure 9 S300, a fixed-point fixed sampling probe, includes:

[0147] S310 controls the moving device to move the sampling probe by a fixed scale value reflected by a fixed point.

[0148] It is understandable that controlling the moving device to insert the sampling probe into the exhaust pipe with a fixed scale value reflected by a fixed point can ensure that the sampling probe will not have insufficient sampling concentration due to insufficient insertion depth, resulting in inaccurate test results.

[0149] S320: After the moving device moves to the distance reflected by the fixed scale value, the control device fixes the sampling probe at the center of the exhaust pipe and prevents it from contacting the inner wall of the exhaust pipe.

[0150] It is understood that a fixing device is a device that can fix the sampling probe in a preset position. For example, the fixing device may include a telescopic fixing rod and a fixing ring, but is not limited to these. Controlling the fixing device to fix the sampling probe in the center of the exhaust pipe and prevent it from contacting the inner wall of the exhaust pipe can prevent contaminants adhering to the inner wall of the exhaust pipe from entering the sampling probe, thus ensuring the accuracy of the test results.

[0151] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0152] Corresponding to the sampling probe insertion depth monitoring method in the environmental exhaust gas detection process described in the above embodiments, this application embodiment also provides a sampling probe insertion depth monitoring system in the environmental exhaust gas detection process. Each unit of the system can realize each step of the sampling probe insertion depth monitoring method in the environmental exhaust gas detection process. Figure 10 The diagram shows a structural block diagram of the sampling probe insertion depth monitoring system for environmental exhaust gas detection provided in the embodiments of this application. For ease of explanation, only the parts related to the embodiments of this application are shown.

[0153] Reference Figure 10 The system includes:

[0154] The acquisition unit is used to acquire activity space information; wherein, the activity space information includes information reflecting the internal physical state of the exhaust pipe of the vehicle being tested.

[0155] The analysis unit is used to obtain fixed points based on the activity space information; wherein, the fixed points reflect the fixed position of the sampling probe in the exhaust pipe during the exhaust gas detection process.

[0156] Control unit for fixing the sampling probe at a fixed point.

[0157] It should be noted that the information interaction and execution process between the above-mentioned units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0158] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0159] This application also provides a device for monitoring the insertion depth of a sampling probe during environmental exhaust gas detection. Figure 11 This is a schematic diagram of a sampling probe insertion depth monitoring device provided in an embodiment of this application for environmental exhaust gas detection. Figure 11 As shown, the sampling probe insertion depth monitoring device in the environmental exhaust gas detection process of this embodiment includes a control device 6. The control device 6 includes at least one processor 60. Figure 11 Only one is shown in the image), at least one memory 61 ( Figure 11 (Only one is shown in the image) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, it causes the sampling probe insertion depth monitoring device in the environmental exhaust gas detection process to perform the steps in any of the above embodiments of the sampling probe insertion depth monitoring method in the environmental exhaust gas detection process, or causes the sampling probe insertion depth monitoring device in the environmental exhaust gas detection process to perform the functions of each unit in the above embodiments of the system.

[0160] For example, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 62 in the control device 6.

[0161] The control device 6 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The control device 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 11This is merely an example of a sampling probe insertion depth monitoring device during environmental exhaust gas testing, and does not constitute a limitation on the sampling probe insertion depth monitoring device during environmental exhaust gas testing. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0162] The processor 60 can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0163] In some embodiments, the memory 61 may be an internal storage unit of the control device 6, such as a hard disk or memory of the control device 6. In other embodiments, the memory 61 may be an external storage device of the control device 6, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the control device 6. Furthermore, the memory 61 may include both internal storage units and external storage devices of the control device 6. The memory 61 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0164] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0165] This application provides a computer program product that, when running during the environmental exhaust gas detection process, enables the sampling probe insertion depth monitoring device to perform the steps described in any of the above method embodiments.

[0166] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to the sampling probe insertion depth monitoring device during the environmental exhaust gas detection process, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0167] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0168] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0169] In the embodiments provided in this application, it should be understood that the sampling probe insertion depth monitoring system, equipment, and method for environmental exhaust gas detection disclosed herein can be implemented in other ways. For example, the embodiments of the sampling probe insertion depth monitoring system and equipment for environmental exhaust gas detection described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0170] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0171] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for monitoring the insertion depth of a sampling probe during environmental exhaust gas detection, characterized in that, include: Acquire activity space information; wherein, the activity space information includes information reflecting the physical state of the internal space of the exhaust pipe of the vehicle being tested; A fixed point is obtained based on the activity space information; wherein, the fixed point reflects the fixed position of the sampling probe in the exhaust pipe during the exhaust gas detection process; The sampling probe is fixed based on the fixed point.

2. The method for monitoring the insertion depth of the sampling probe during environmental exhaust gas detection as described in claim 1, characterized in that, Before acquiring the activity space information, the sampling probe insertion depth monitoring method during the environmental exhaust gas detection process further includes: The cleaning device is controlled to clean the interior of the exhaust pipe of the vehicle being tested, and the cleaning depth is not less than p millimeters extending into the interior of the exhaust pipe from the position of the three-way catalytic converter or the tail of the exhaust pipe; wherein p ≥ 600.

3. The method for monitoring the insertion depth of the sampling probe during environmental exhaust gas detection as described in claim 1, characterized in that, The acquisition of activity space information includes: Obtain an exhaust pipe model; wherein the exhaust pipe model reflects the internal space of the exhaust pipe; Acquire inner wall image information; wherein, the inner wall image information reflects the inner wall image of the exhaust pipe; The exhaust pipe model and the inner wall image information are confirmed as the activity space information.

4. The method for monitoring the insertion depth of the sampling probe during environmental exhaust gas detection as described in claim 3, characterized in that, The process of obtaining the exhaust pipe model includes: A first control command is sent to the mobile device, and a second control command is sent to the scanning device simultaneously. The first control command instructs the mobile device to move the scanning device, image acquisition device, and sampling probe from the insertion point of the exhaust pipe towards the end of the exhaust pipe furthest from the exhaust outlet by *i* millimeters, and then stop moving. During the movement, the movement is paused for 5 seconds after every *j* millimeters of movement. *i* is a positive integer, *i* ≥ 600, and *j* is a positive integer, *j* ≥ 50. The scanning device is capable of scanning the internal structure of the exhaust pipe, and the image acquisition device is capable of acquiring an image of the inner wall of the exhaust pipe. The second control command instructs the scanning device to scan the exhaust pipe. The system receives scanning data sent by the scanning device and obtains the exhaust pipe model based on the scanning data; wherein the exhaust pipe model includes a three-dimensional model reflecting the internal structure of the exhaust pipe, a starting position, and an ending position, the starting position being the position of the sampling probe inside the exhaust pipe when the second control command is sent, and the ending position being the position of the sampling probe inside the exhaust pipe after the moving device moves i millimeters.

5. The method for monitoring the insertion depth of the sampling probe during environmental exhaust gas detection as described in claim 4, characterized in that, The acquisition of inner wall image information includes: When sending the first control command, a third control command is simultaneously sent to the image acquisition device; wherein, the third control command is used to instruct the image acquisition device to take pictures of the inner wall of the exhaust pipe when the mobile device stops moving in order to obtain multiple segmented images, wherein the segmented images are the images acquired by the image acquisition device each time the mobile device stops moving. The image acquisition device receives all the segmented images and stitches them together in the order of acquisition time to obtain the inner wall image information. The inner wall image information includes a planar image reflecting the structure of the inner wall of the exhaust pipe, as well as a starting end and a ending end. The starting end is the end of the planar image that is closer to the tail of the exhaust pipe, and the ending end is the end of the planar image that is farther away from the tail of the exhaust pipe.

6. The method for monitoring the insertion depth of the sampling probe during environmental exhaust gas detection as described in claim 5, characterized in that, The process of obtaining fixed points based on the activity space information includes: The inner wall plane information is obtained by unfolding the exhaust pipe model along its length; wherein, the unfolding operation is an operation that can transform the exhaust pipe model from a pipe model into a planar model, and the inner wall plane information includes a planar model reflecting the inner wall structure of the exhaust pipe, as well as a starting point and an ending point, wherein the starting point is the vertical projection of the starting position on the planar model, and the ending point is the vertical projection of the ending position on the planar model. The planar model is input into a first defect recognition model to obtain a first defect image; wherein, the first defect recognition model is a data model obtained by machine learning, and the first defect image includes the planar model and at least one first defect information marked on the planar model, the first defect information including a first defect range obtained by the first defect recognition model, a weight value corresponding to the first defect range, a first starting point corresponding to the starting point position, and a first ending point corresponding to the ending point position. The planar image is input into a second defect recognition model to obtain a second defect image; wherein, the second defect recognition model is a data model obtained through machine learning, and the second defect image includes the planar image and at least one second defect information marked on the planar image, the second defect information including a second defect range obtained by the second defect recognition model, a weight value corresponding to the second defect range, a second starting point corresponding to the starting point position, and a second ending point corresponding to the ending point position; The fixed point is obtained based on the first defect image and the second defect image.

7. The method for monitoring the insertion depth of the sampling probe during environmental exhaust gas detection as described in claim 6, characterized in that, The process of obtaining the fixed point based on the first defective image and the second defective image includes: An analysis environment is established based on the first defective image and the second defective image; wherein, the analysis environment includes coordinate axes on the same plane, the first defective image and the second defective image, the scale unit of the coordinate axes is millimeters, the scale coordinate value of the origin of the coordinate axes is equal to the scale coordinate value of the first starting point of the first defective image and the second starting point of the second defective image, and the extension direction of the coordinate axes is consistent with and parallel to the extension direction from the first starting point to the first ending point and the extension direction from the second starting point to the second ending point; The analysis range is obtained based on the coordinate axis, wherein the analysis range is the range formed by extending a line perpendicular to the coordinate axis with a base length of k mm and the two endpoints perpendicular to the coordinate axis and in the same plane as the first defect image and the second defect image, where k is a positive integer and k≥10; The fixed point is obtained based on the analysis environment and analysis range.

8. The method for monitoring the insertion depth of the sampling probe during environmental exhaust gas detection as described in claim 7, characterized in that, The process of obtaining the fixed point based on the analysis environment and analysis range includes: The left endpoint of the analysis range is set to 400 mm, and the right endpoint of the analysis range is set to 400+k mm; wherein, the left endpoint is the endpoint of the bottom edge of the analysis range that is closest to the origin of the coordinate axis, and the right endpoint is the endpoint of the bottom edge of the analysis range that is furthest from the origin of the coordinate axis. Step a: Determine whether the perpendicular line drawn from the left endpoint and the right endpoint to the coordinate axis, which is in the same plane as the first defect image and the second defect image, contacts the first defect range of the first defect information in the first defect image or the second defect range of the second defect information in the second defect image in the analysis environment; If the vertical line contacts the first defect range of the first defect information in the first defect image or the second defect range of the second defect information in the second defect image, then the weight of the portion of the first defect range or the second defect range that contacts the vertical line and is located within the analysis range is calculated separately to obtain the segmentation weight. The segmentation weight is then added to the corresponding weight values ​​of the first defect range and the second defect range that are located within the analysis range and do not contact the vertical line to obtain the total weight value. If the vertical line does not contact the first defect range of the first defect information in the first defect image and the second defect range of the second defect information in the second defect image, then the weight values ​​corresponding to the first defect range and the second defect range included in the analysis range are added together to obtain the total weight value; Step b: Add the calculated total weight value to the weight table; wherein the weight table includes the total weight value and the scale values ​​of the left and right endpoints of the analysis range corresponding to the total weight value; Step c: Determine whether the scale value of the right endpoint of the analysis range is equal to the scale value of the first endpoint of the first defect image or the scale value of the second endpoint of the second defect image; If the scale value of the right endpoint is equal to the scale value of the first endpoint of the first defective image or the scale value of the second endpoint of the second defective image, then the fixed point is obtained based on the weight table. If the scale value of the right endpoint is not equal to the scale value of the first endpoint of the first defective image and the scale value of the second endpoint of the second defective image, then add m to the scale values ​​of the left endpoint and the right endpoint and repeat steps a, b and c; where m is a positive integer and m≥1.

9. The method for monitoring the insertion depth of the sampling probe during environmental exhaust gas detection as described in claim 8, characterized in that, The process of obtaining the fixed point based on the weight table includes: By comparing multiple total weight values ​​in the weight table, the minimum weight value is obtained; wherein, the minimum weight value is the total weight value with the smallest value among multiple total weight values; Add the scale values ​​of the left and right endpoints of the analysis range corresponding to the minimum weight value, and then divide by 2 to obtain a fixed scale value. The position inside the exhaust pipe reflected by the fixed scale value is identified as the fixed point; And / or, fixing the sampling probe based on the fixed point includes: The moving device is controlled to move the sampling probe according to the fixed scale value reflected by the fixed point; After the moving device moves to the distance reflected by the fixed scale value, the fixing device is controlled to fix the sampling probe in the center of the exhaust pipe and prevent it from contacting the inner wall of the exhaust pipe.

10. A sampling probe insertion depth monitoring device for environmental exhaust gas detection, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 9.

Images