Active infrared optical detection device for gas leakage in pipeline

Abstract

The invention relates to the technical field of pipeline leakage detection, and discloses an active infrared optical detection device for gas leakage in a pipeline, which comprises a detection body, the detection body comprises a driving motor, a motor fixing ring, a one-way rotating mechanism, a periscopic infrared structure, an infrared camera structure and a camera fixing seat, the driving motor is connected with the one-way rotating mechanism, and the motor fixing ring is connected with the one-way rotating mechanism; the driving motor is used for driving the one-way rotating mechanism, one end of the periscopic infrared mechanism is connected with the one-way rotating mechanism, the other end of the periscopic infrared mechanism is connected with the infrared camera shooting mechanism, the motor shaft is sleeved with the rotating shaft, and the rotating shaft is meshed with the one-way rotating disc. One end of the deflector rod spring is fixedly connected with the deflector rod, and the other end of the deflector rod spring is fixedly connected with the one-way rotating turntable. According to the invention, multi-angle adjustment is carried out on active infrared rays, so that the reliability of an imaging view field is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline leakage detection, and more particularly, to an active infrared optical detection device for gas leakage inside a pipeline. Background Art

[0002] In closed environments such as urban gas pipe networks and industrial transportation pipelines, the leakage of natural gas (mainly composed of methane CH4) not only causes energy waste but also may lead to fire or explosion accidents. Current gas leakage detection technologies can be divided into external detection technologies and internal detection technologies. However, there are certain limitations in detecting pipeline leakage from the outside. For example, it is impossible to detect buried pipelines. And internal detection technologies include non-dispersive infrared sensors, ultrasonic leakage detectors, and active infrared technologies. Compared with external detection technologies, internal detection technologies can achieve leakage detection of buried gas pipelines. However, when using active infrared, due to the obstruction of the internal space of the pipeline, it is impossible to adjust the active infrared at multiple angles, resulting in an obstructed imaging field of view and ineffective detection and warning.

[0003] Therefore, it is necessary to design an active infrared optical detection device for gas leakage inside a pipeline to solve the problems existing in the current technology. Summary of the Invention

[0004] In view of this, the present invention proposes an active infrared optical detection device for gas leakage inside a pipeline, aiming to solve the problem that due to the obstruction of the internal space of the pipeline, it is impossible to adjust the active infrared at multiple angles, resulting in an obstructed imaging field of view and ineffective detection and warning.

[0005] The present invention proposes an active infrared optical detection device for gas leakage inside a pipeline, comprising:

[0006] A detection body, the detection body includes a driving motor, a motor fixing ring, a one-way rotation mechanism, a periscope infrared structure, an infrared camera structure, and a camera fixing seat;

[0007] The driving motor is connected to the one-way rotation mechanism, the driving motor is used to drive the one-way rotation mechanism, and the motor fixing ring is used to fix the driving motor;

[0008] One end of the periscope infrared mechanism is connected to the one-way rotation mechanism, the other end of the periscope infrared mechanism is connected to the infrared camera mechanism, the bottom of the infrared camera mechanism is fixedly connected to the top of the camera fixing seat, the driving motor is provided with a motor shaft, and the motor shaft penetrates through the motor fixing ring;

[0009] The one-way rotation mechanism includes a rotation mechanism upper cover, a rotation mechanism lower cover, a rotation module, a slider, and a slider spring;

[0010] The upper cover of the rotating mechanism is fixedly connected to the lower cover of the rotating mechanism. The rotating module is arranged inside the enclosed space formed by the upper cover of the rotating mechanism and the lower cover of the rotating mechanism. A plurality of slider springs are provided, and a plurality of sliders are provided. Each slider spring is fixedly connected to the side wall of the lower cover of the rotating mechanism, and each slider spring is fixedly connected to a slider.

[0011] The rotating module includes a rotating shaft, a lever spring, a lever, a unidirectional rotating turntable and a groove.

[0012] The motor shaft sleeves the rotating shaft. The rotating shaft is engaged with the unidirectional rotating turntable. The unidirectional rotating turntable is provided with the groove. The rotating shaft is fixedly connected to the lever. One end of the lever spring is fixedly connected to the lever, and the other end of the lever spring is fixedly connected to the unidirectional rotating turntable.

[0013] Furthermore, the active infrared optical detection device for gas leakage in the pipeline further includes:

[0014] The periscope infrared mechanism includes a periscope infrared body and a vertical reflector.

[0015] The vertical reflector is arranged inside the periscope infrared body.

[0016] The periscope infrared body includes a periscope structure housing, an infrared light source, an infrared light homogenizing plate, a single-sided concave lens and a single-sided convex lens.

[0017] The infrared light source is arranged inside the periscope structure housing. The infrared light homogenizing plate is attached to the infrared light source. The single-sided concave lens and the single-sided convex lens are arranged inside the periscope structure housing.

[0018] The infrared camera structure is provided with a data output serial port.

[0019] A control module is electrically connected to the drive motor, the periscope infrared structure and the infrared camera structure. The control module is used to control the working states of the drive motor and the periscope infrared structure.

[0020] Furthermore, the control module includes:

[0021] An acquisition unit configured to acquire the current infrared image at the current moment in the pipeline and the previous infrared image at the same angle at the previous moment.

[0022] A judgment unit configured to compare the current infrared image with the previous infrared image, judge whether to adjust the motor speed of the drive motor according to the comparison result, and when it is determined that adjustment is required, determine a speed adjustment factor based on the current infrared image and the previous infrared image.

[0023] A processing unit, configured to obtain a rotational speed data set, determine a rotational speed prediction adjustment factor based on the rotational speed data set and a rotational speed model, determine a factor deviation value according to the rotational speed adjustment factor and the rotational speed prediction adjustment factor, when the factor deviation value is less than a factor deviation threshold, obtain all historical motor rotational speeds, analyze all historical motor rotational speeds, determine an adjustment coefficient of the rotational speed adjustment factor based on the analysis result, and adjust the rotational speed adjustment factor based on the adjustment coefficient to determine a target motor rotational speed;

[0024] An early warning unit, configured to obtain infrared images at at least three angles based on the target motor rotational speed, preprocess all the infrared images, and determine an early warning level according to the result of the preprocessing.

[0025] Further, when judging whether to adjust the motor rotational speed of the drive motor according to the comparison result, it includes:

[0026] If the pixel points of the current infrared image are the same as those of the previous infrared image, the judging unit determines not to adjust the motor rotational speed;

[0027] If the pixel points of the current infrared image are different from those of the previous infrared image, the judging unit determines to adjust the motor rotational speed.

[0028] Further, when determining a rotational speed adjustment factor based on the current infrared image and the previous infrared image, it includes:

[0029] The judging unit extracts the different pixel points of the current infrared image and the previous infrared image, and counts the number of different pixel points;

[0030] A first preset number of differences and a second preset number of differences are preset in advance, and the first preset number of differences is greater than the second preset number of differences;

[0031] When the number of differences is greater than or equal to the first preset number of differences, the first rotational speed coefficient is used as the rotational speed adjustment factor;

[0032] When the number of differences is less than the first preset number of differences and greater than the second preset number of differences, the second rotational speed coefficient is used as the rotational speed adjustment factor;

[0033] When the number of differences is less than or equal to the second preset number of differences, the third rotational speed coefficient is used as the rotational speed adjustment factor;

[0034] Wherein, the value range of the rotational speed coefficient is: 1 < the third rotational speed coefficient < the second rotational speed coefficient < the first rotational speed coefficient.

[0035] Further, when determining the rotational speed prediction adjustment factor based on the rotational speed data set and the rotational speed model, it includes:

[0036] The processing unit divides the rotational speed data set into a training set and a test set, and uses grid search to find hyperparameters to establish a decision tree model, fits the decision tree model according to the training set, substitutes the test set into the decision tree model and evaluates it;

[0037] When the evaluation value reaches the preset evaluation threshold, determine the rotational speed prediction adjustment factor according to the number of differences.

[0038] Further, when determining the factor deviation value according to the rotational speed adjustment factor and the rotational speed prediction adjustment factor, it includes:

[0039] The processing unit determines the ratio of the rotational speed adjustment factor and the rotational speed prediction adjustment factor as the factor deviation value, and presets the factor deviation threshold;

[0040] When the factor deviation value is greater than or equal to the factor deviation threshold, it is determined not to adjust the rotational speed adjustment factor, and the product value of the rotational speed adjustment factor and the motor rotational speed is determined as the target motor rotational speed;

[0041] When the factor deviation value is less than the factor deviation threshold, it is determined to adjust the rotational speed adjustment factor.

[0042] Further, when determining the adjustment coefficient of the rotational speed adjustment factor based on the analysis result, adjusting the rotational speed adjustment factor based on the adjustment coefficient, and determining the target motor rotational speed, it includes:

[0043] The processing unit analyzes all historical motor rotational speeds to determine the overclocking rotational speed, the default rotational speed, and the low-frequency rotational speed, constructs all overclocking rotational speeds into a first historical rotational speed set, constructs all low-frequency rotational speeds into a second historical rotational speed set, obtains the first rotational speed average value in the first historical rotational speed set, and obtains the second rotational speed average value in the second historical rotational speed set;

[0044] Obtain the first difference between the first rotational speed average value and the default rotational speed, and obtain the second difference between the default rotational speed and the second rotational speed average value, obtain the absolute value of the ratio of the first difference to the second difference, and use the absolute value as the adjustment coefficient;

[0045] Use the product value of the adjustment coefficient and the rotational speed adjustment factor as the target adjustment factor, and determine the product value of the target adjustment factor and the motor rotational speed as the target motor rotational speed.

[0046] Further, when preprocessing all infrared images, it includes:

[0047] The preprocessing includes denoising and geometric correction. The warning unit extracts feature points from all the preprocessed infrared images using the Speeded Up Robust Features (SURF) algorithm, and matches the extracted feature points based on the Random Sample Consensus (RANSAC) algorithm to determine the matching information between each infrared image. Based on the matching information, all the preprocessed infrared images are merged to determine a merged image.

[0048] Image processing is performed on the merged image to determine a leakage image. The image processing includes removing stitching seams and sharpening the image edges.

[0049] Further, when determining the warning level according to the results of the preprocessing, it includes:

[0050] The warning unit obtains a qualified pipeline image corresponding to the leakage image;

[0051] All the pixels to be detected in the leakage image are extracted, and all the qualified pixels corresponding to the pixels to be detected are extracted from the qualified pipeline image. The pixel values to be detected corresponding to all the pixels to be detected are determined, and the qualified pixel values corresponding to all the qualified pixels are determined;

[0052] The number of pixels to be detected whose pixel values to be detected are not equal to the qualified pixel values is counted. A first preset number of pixels to be detected and a second preset number of pixels to be detected are preset in advance. The first preset number of pixels to be detected is greater than the second preset number of pixels to be detected;

[0053] When the number of pixels to be detected is greater than or equal to the first preset number of pixels to be detected, the pipeline is determined to have a first-level leakage warning;

[0054] When the number of pixels to be detected is less than the first preset number of pixels to be detected and greater than the second preset number of pixels to be detected, the pipeline is determined to have a second-level leakage warning;

[0055] When the number of pixels to be detected is less than or equal to the second preset number of pixels to be detected, the pipeline is determined to have a third-level leakage warning;

[0056] The urgency of the first-level leakage warning, the second-level leakage warning, and the third-level leakage warning decreases in sequence.

[0057] Compared with the prior art, the beneficial effects of the present invention are as follows: By adopting the internal detection technology, it can penetrate into the interior of the pipeline. Whether it is an above-ground pipeline or a buried pipeline, gas leakage detection can be carried out, effectively making up for the deficiencies of the external detection technology and expanding the applicable scope of detection. The periscope infrared mechanism can be rotated and adjusted at multiple angles, and can collect infrared light at different angles inside the pipeline in all directions, effectively expanding the imaging field of view and enabling comprehensive detection of each area inside the pipeline, so as to timely discover gas leakage points and give corresponding warnings, ensuring the operation of the gas pipeline network and industrial transportation pipelines. Brief Description of the Drawings

[0058] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0059] Figure 1 is a schematic structural diagram of an active infrared optical detection device for gas leakage in a pipeline provided by an embodiment of the present invention;

[0060] Figure 2 is an exploded view of an active infrared optical detection device for gas leakage in a pipeline provided by an embodiment of the present invention;

[0061] Figure 3 is a schematic structural diagram of a unidirectional rotation mechanism with the upper cover of the rotation mechanism removed provided by an embodiment of the present invention;

[0062] Figure 4 is a top view of a unidirectional rotation mechanism with the upper cover of the rotation mechanism removed provided by an embodiment of the present invention;

[0063] Figure 5 is an exploded view of a periscope infrared mechanism provided by an embodiment of the present invention;

[0064] Figure 6 is a schematic structural diagram of a periscope infrared mechanism provided by an embodiment of the present invention;

[0065] Figure 7 is a functional block diagram of a control module provided by an embodiment of the present invention.

[0066] In the figure, 1, detection body; 2, drive motor; 3, motor fixing ring; 4, unidirectional rotation mechanism; 5, periscope infrared mechanism; 6, infrared camera mechanism; 7, camera fixing seat; 201, motor shaft; 401, lower cover of the rotation mechanism; 402, upper cover of the rotation mechanism; 403, rotating shaft; 404, slider spring; 407, lever spring; 408, lever; 409, unidirectional rotation turntable; 410, slider; 411, groove; 501, periscope structure housing; 502, infrared light source; 503, infrared light homogenizing plate; 504, vertical reflecting mirror; 505, single-sided concave lens; 506, single-sided convex lens; 601, data output serial port. Detailed Description of the Embodiments

[0067] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0068] Referring to Figures 1-4 As shown, in some embodiments of the present application, an active infrared optical detection device for gas leakage in a pipeline includes:

[0069] A detection body 1, the detection body 1 includes a drive motor 2, a motor fixing ring 3, a one-way rotation mechanism 4, a periscope infrared structure, an infrared camera structure, and a camera fixing seat 7. The drive motor 2 is connected to the one-way rotation mechanism 4. The drive motor 2 is used to drive the one-way rotation mechanism 4. The motor fixing ring 3 is used to fix the drive motor 2. One end of the periscope infrared mechanism 5 is connected to the one-way rotation mechanism 4, and the other end of the periscope infrared mechanism 5 is connected to the infrared camera mechanism 6. The bottom of the infrared camera mechanism 6 is fixedly connected to the top of the camera fixing seat 7. The drive motor 2 is provided with a motor shaft 201, and the motor shaft 201 passes through the motor fixing ring 3. The one-way rotation mechanism 4 includes a rotation mechanism upper cover 402, a rotation mechanism lower cover 401, a rotation module, a slider 410, and a slider spring 404. The rotation mechanism upper cover 402 is fixedly connected to the rotation mechanism lower cover 401. The rotation module is arranged inside the enclosed space formed by the rotation mechanism upper cover 402 and the rotation mechanism lower cover 401. A plurality of slider springs 404 are provided, and a plurality of sliders 410 are provided. Each slider spring 404 is fixedly connected to the side wall of the rotation mechanism lower cover 401, and each slider spring 404 is fixedly connected to a slider 410. The rotation module includes a rotation shaft 403, a lever spring 407, a lever 408, a one-way rotation turntable 409, and a groove 411. The motor shaft 201 is sleeved with the rotation shaft 403. The rotation shaft 403 is engaged with the one-way rotation turntable 409. The one-way rotation turntable 409 is provided with a groove 411. The rotation shaft 403 is fixedly connected to the lever 408. One end of the lever spring 407 is fixedly connected to the lever 408, and the other end of the lever spring 407 is fixedly connected to the one-way rotation turntable 409.

[0070] Specifically, the motor shaft 201 passes through the motor fixing ring 3. The motor fixing ring 3 serves to fix the driving motor 2 and ensure the stability of the driving motor 2 during operation. The motor shaft 201 is sleeved with the rotating shaft 403 and meshes with the rotating shaft 403. When the driving motor 2 rotates, the rotation of the motor shaft 201 drives the rotating shaft 403 to rotate synchronously. The rotating shaft 403 meshes with the one-way rotating turntable 409. When the rotating shaft 403 rotates, the lever 408 rotates synchronously. The lever 408 is responsible for stretching the lever spring 407. Preferably, there are four slider springs 404, and the slider springs 404 are axially symmetric about the center of the one-way rotating turntable 409. Preferably, there are four sliders 410. When the lever 408 rotates to the groove 411 caught by the slider 410, the lever 408 pushes the tip part of the slider 410, and the slider 410 is separated from the groove 411 due to the compression of the slider spring 404. At this time, the one-way rotating turntable 409 rotates under the rotation of the motor shaft 201 and the pulling force of the lever spring 407. During the rotation, the slider 410 compressed by the slider spring 404 is released and fits the one-way rotating turntable 409. Under the elastic action of the slider spring 404, the smooth progress of the one-way rotation is ensured, and the reverse rotation of the one-way rotating turntable 409 is prevented. Moreover, the rotation of the one-way rotating turntable 409 drives its groove 411 to the next slider 410, so that the next slider 410 continues to catch the groove 411, further preventing the reverse rotation of the one-way rotating turntable 409 and ensuring the one-way rotation of the one-way rotating turntable 409. The periscope infrared mechanism 5 and the infrared imaging mechanism 6 work together. The rotation of the one-way rotating mechanism 4 drives the rotation of the periscope infrared mechanism 5. The camera fixing seat 7 is used to fix the infrared imaging mechanism 6 to ensure its stability during detection. The periscope infrared mechanism 5 collects and conducts the infrared light in the pipeline, so as to accurately capture the infrared image. The infrared light in different areas inside the pipeline at different angles is collected, ensuring the reliability of the leakage detection.

[0071] It can be understood that by adopting the internal detection technology, it is possible to penetrate deep into the pipeline interior. Whether it is an above-ground pipeline or a buried pipeline, gas leakage detection can be carried out, effectively making up for the deficiencies of the external detection technology and expanding the applicable scope of the detection, enabling the periscope infrared mechanism 5 to perform multi-angle rotation adjustment. The infrared light at different angles inside the pipeline can be collected in all directions, effectively expanding the imaging field of view, enabling comprehensive detection of each area inside the pipeline, so as to timely discover gas leakage points and give corresponding early warnings, ensuring the operation of closed environments such as gas pipe networks and industrial transportation pipelines.

[0072] Refer to Figures 5-6As shown, in some embodiments of the present application, the active infrared optical detection device for gas leakage in a pipeline further includes: The periscope infrared mechanism 5 includes a periscope infrared body and a vertical reflector 504. The vertical reflector 504 is arranged inside the periscope infrared body. The periscope infrared body includes a periscope structure housing 501, an infrared light source 502, an infrared light homogenizing plate 503, a single-sided concave lens 505, and a single-sided convex lens 506. The infrared light source 502 is arranged inside the periscope structure housing 501. The infrared light homogenizing plate 503 is attached to the infrared light source 502. The single-sided concave lens 505 and the single-sided convex lens 506 are arranged inside the periscope structure housing 501. The infrared camera structure is provided with a data output serial port 601. The control module is electrically connected to the drive motor 2, the periscope infrared structure, and the infrared camera structure. The control module is used to control the working states of the drive motor 2 and the periscope infrared structure.

[0073] Specifically, the infrared light source 502 emits infrared light inside the periscope structure housing 501. The infrared light homogenizing plate 503 is attached to the infrared light source 502. The core of gas leakage detection is to detect the leakage of methane (CH4). The infrared absorption peak of methane is located at 3.3 μm (near the mid-infrared band). If the wavelength emitted by the infrared light source matches the absorption peak of methane, the leaked methane will absorb the infrared light of this wavelength. Therefore, the infrared light source 502 is set to 3.3 μm ± 0.1 μm to better detect gas leakage. The infrared light is homogenized to make the light distribution more uniform. The light processed by the infrared light homogenizing plate 503 is then refracted and optically processed by the single-sided concave lens 505 and the single-sided convex lens 506 to change the light propagation direction and focusing situation. The vertical reflector 504 is arranged inside the periscope infrared body to reflect the infrared light processed by the single-sided lens in the vertical direction to better detect the leakage situation. Figure 6 The structure diagram of the periscope infrared mechanism is shown, and its specific structure is shown inside the periscope infrared body. After being processed by the periscope infrared mechanism 5, the collected image and other data information are output through the data output serial port 601. The control module is electrically connected to the drive motor 2, the periscope infrared structure, and the infrared camera structure. The control module can control parameters such as the start-stop and rotation speed of the drive motor 2, and then drive the periscope infrared mechanism 5 to perform multi-angle rotation detection. At the same time, the control module can also control the working states of components such as the infrared light source 502 in the periscope infrared structure to ensure the coordinated and stable operation of the entire detection device.

[0074] Refer to Figure 7As shown, in some embodiments of the present application, the control module includes: an acquisition unit configured to acquire the current infrared image at the current moment in the pipeline and the previous infrared image at the same angle at the previous moment; a judgment unit configured to compare the current infrared image with the previous infrared image and determine whether to adjust the motor speed of the drive motor 2 according to the comparison result. When it is determined that adjustment is required, a speed adjustment factor is determined based on the current infrared image and the previous infrared image; a processing unit configured to obtain a speed data set and determine a predicted speed adjustment factor based on the speed data set and a speed model, determine a factor deviation value according to the speed adjustment factor and the predicted speed adjustment factor. When the factor deviation value is less than the factor deviation threshold, all historical motor speeds are obtained, and all historical motor speeds are analyzed. Based on the analysis result, an adjustment coefficient of the speed adjustment factor is determined, and the speed adjustment factor is adjusted based on the adjustment coefficient to determine the target motor speed; an early warning unit configured to acquire infrared images at at least three angles based on the target motor speed, preprocess all the infrared images, and determine the early warning level according to the result of the preprocessing.

[0075] Specifically, the acquisition unit is responsible for collecting infrared images inside the pipeline in real time. It obtains the current infrared image at the current moment and simultaneously records the previous infrared image at the same angle at the previous moment, providing basic data for subsequent comparative analysis, effectively capturing the changes in the infrared state at the same position inside the pipeline at different times. The judgment unit compares the current infrared image with the previous infrared image. If a difference is found between the images, it indicates that there is a gas leak or other situations in the detection area involved by the device inside the pipeline. At this time, it is necessary to adjust the motor speed of the drive motor 2. The motor speed of the drive motor 2 usually maintains the rated speed when there is no leakage. The speed adjustment factor is determined by comparing the degree of difference between the images to change the motor speed and thus accelerate the detection of the inside of the pipeline. The processing unit obtains the speed data set, which includes key data such as pipeline pressure, pipeline flow rate, historical speed adjustment factors, and the corresponding motor speeds. The speed model is used to predict the future speed adjustment requirements, determine the speed prediction adjustment factor, and then compare the speed adjustment factor with the speed prediction adjustment factor to determine the factor deviation value. The factor deviation value reflects the deviation between the prediction of the big data model and the actually calculated speed adjustment factor. When the factor deviation value is less than the factor deviation threshold, it indicates that the current speed adjustment strategy is relatively close to the prediction situation, but further adjustment is still required. At this time, the processing unit will collect all the historical motor speeds and conduct an analysis, determine the adjustment coefficient of the speed adjustment factor according to the analysis results, and adjust the speed adjustment factor through this adjustment coefficient to determine a stable and reliable target motor speed, and then drive the periscope infrared mechanism 5 to perform multi-angle rotation detection. Since the slider spring 404 is axisymmetric about the center of the one-way rotating turntable 409, the rotation angles are 90°, 180°, 270°, and 360° in four directions. The warning unit obtains infrared images at at least three of these four angles according to the determined target motor speed, and preprocesses these infrared images, such as noise reduction and other operations. By analyzing the characteristics of the preprocessed images, the degree of gas leakage is judged and the corresponding warning level is determined.

[0076] It can be understood that by determining the target motor speed and then driving the periscope infrared mechanism 5 to perform multi-angle rotation detection, it is possible to accurately capture the signs of gas leakage inside the pipeline, avoid misjudgment or missed judgment caused by single-image judgment, improve the accuracy of detection. Based on image comparison and speed model prediction, the target motor speed is finally determined, enabling the device to intelligently adjust the operating state according to the actual detection situation, ensuring comprehensive detection under different working conditions, and improving the detection efficiency and coverage.

[0077] In some embodiments of the present application, when determining whether to adjust the motor speed of the drive motor 2 according to the comparison result, it includes: when the pixel points of the current infrared image are the same as those of the previous infrared image, the judgment unit determines not to adjust the motor speed; when the pixel points of the current infrared image are different from those of the previous infrared image, the judgment unit determines to adjust the motor speed.

[0078] In some embodiments of the present application, when determining the speed adjustment factor based on the current infrared image and the previous infrared image, it includes: the judgment unit extracts the different differential pixel points of the current infrared image and the previous infrared image, and counts the number of differential pixel points. A first preset number of differences and a second preset number of differences are preset in advance, and the first preset number of differences is greater than the second preset number of differences. When the number of differences is greater than or equal to the first preset number of differences, the first speed coefficient is used as the speed adjustment factor; when the number of differences is less than the first preset number of differences and greater than the second preset number of differences, the second speed coefficient is used as the speed adjustment factor; when the number of differences is less than or equal to the second preset number of differences, the third speed coefficient is used as the speed adjustment factor, where the value range of the speed coefficient is: 1 < third speed coefficient < second speed coefficient < first speed coefficient.

[0079] Specifically, by comparing whether the pixel points of the current infrared image and the previous infrared image are the same to determine whether to adjust the motor speed, a quick judgment can be made. When the pixel points are the same, it indicates that the state of the corresponding area in the pipeline is stable and there is no need to adjust the motor speed, avoiding unnecessary adjustment operations on the drive motor 2. Determining the speed adjustment factor based on the number of differential pixel points realizes precise adjustment of the motor speed according to the degree or range of gas leakage. When the number of differences is large (greater than or equal to the first preset number of differences), the larger first speed coefficient is used as the speed adjustment factor, which means that the motor speed will be adjusted significantly, and the detection speed of the device for this area can be increased to quickly and comprehensively check. When the number of differences is in the middle range (less than the first preset number of differences and greater than the second preset number of differences), the moderate second speed coefficient is used. When the number of differences is small (less than or equal to the second preset number of differences), the smaller third speed coefficient is used. This hierarchical adjustment method enables the device to reasonably allocate detection resources and operate at an appropriate speed in different leakage situations, ensuring both the comprehensiveness of detection and the detection efficiency, thereby improving the reliability and accuracy of the entire gas leakage detection system.

[0080] In some embodiments of the present application, when determining the rotational speed prediction adjustment factor based on the rotational speed data set and the rotational speed model, it includes: the processing unit divides the rotational speed data set into a training set and a test set, and uses grid search to find hyperparameters to establish a decision tree model, fits the decision tree model according to the training set, substitutes the test set into the decision tree model and evaluates it. When the evaluation value reaches the preset evaluation threshold, the rotational speed prediction adjustment factor is determined according to the number of differences.

[0081] Specifically, the rotational speed data set includes key data such as pipeline pressure, pipeline flow rate, historical rotational speed adjustment factor, and the corresponding motor rotational speed. Grid search exhaustively searches for the best parameter combination in the parameter space. Usually, 70%-80% of the data is used as the training set, and the rest is used as the test set. Ensure that both the training set and the test set contain a variety of data to improve the generalization ability of the model. The training set is used to fit the decision tree model, while the test set is used to evaluate the performance of the trained model. During the fitting process, the model will try to learn the patterns and relationships in the data to improve its prediction or classification ability. The data in the test set is used to evaluate the model, and the evaluation metrics include accuracy, loss function value, recall rate, etc., which are used to measure the performance of the model. The preset evaluation threshold is set according to the corresponding evaluation metrics. For example: the model needs to have an accuracy of 0.8, and the cross-entropy loss is between 0.5-1.5, etc. When the evaluation value reaches the preset evaluation threshold, it is considered that the model has reached a stable performance and can effectively capture the complex relationships in the data. At this time, the decision tree model is determined as the rotational speed model, and the number of differences is substituted into the rotational speed model to determine the rotational speed prediction adjustment factor, avoiding judgment errors and thus improving the detection efficiency.

[0082] In some embodiments of the present application, when determining the factor deviation value according to the rotational speed adjustment factor and the rotational speed prediction adjustment factor, it includes: the processing unit determines the ratio of the rotational speed adjustment factor and the rotational speed prediction adjustment factor as the factor deviation value, and pre-sets a factor deviation threshold. When the factor deviation value is greater than or equal to the factor deviation threshold, it is determined that the rotational speed adjustment factor is not adjusted, and the product value of the rotational speed adjustment factor and the motor rotational speed is determined as the target motor rotational speed. When the factor deviation value is less than the factor deviation threshold, it is determined that the rotational speed adjustment factor is adjusted.

[0083] In some embodiments of the present application, when determining the adjustment coefficient of the rotation speed adjustment factor based on the analysis result, adjusting the rotation speed adjustment factor based on the adjustment coefficient, and determining the target motor rotation speed, it includes: The processing unit analyzes all historical motor rotation speeds to determine the overclocking rotation speed, the default rotation speed, and the low-frequency rotation speed. Construct all overclocking rotation speeds into the first historical rotation speed set, construct all low-frequency rotation speeds into the second historical rotation speed set, obtain the first rotation speed average value in the first historical rotation speed set, and obtain the second rotation speed average value in the second historical rotation speed set. Obtain the first difference between the first rotation speed average value and the default rotation speed, and obtain the second difference between the default rotation speed and the second rotation speed average value. Obtain the absolute value of the ratio of the first difference to the second difference, and use the absolute value as the adjustment coefficient. Use the product value of the adjustment coefficient and the rotation speed adjustment factor as the target adjustment factor, and determine the product value of the target adjustment factor and the motor rotation speed as the target motor rotation speed.

[0084] Specifically, when the processing unit calculates the factor deviation value, it compares the rotation speed adjustment factor with the rotation speed prediction adjustment factor, and uses the ratio of the two as the factor deviation value. This ratio reflects the deviation degree between the rotation speed adjustment requirement obtained by comparing the current image and the rotation speed adjustment requirement obtained by model prediction. The preset factor deviation threshold is the standard for judging whether it is necessary to further adjust the rotation speed adjustment factor. The factor deviation threshold is preferably 0.8. When the factor deviation value is greater than or equal to the factor deviation threshold, it means that the rotation speed adjustment factor is large and can increase the motor rotation speed. At this time, the rotation speed adjustment factor is not modified, and the product of the rotation speed adjustment factor and the current motor rotation speed is directly used as the target motor rotation speed to quickly adjust the motor rotation speed. When the factor deviation value is less than the factor deviation threshold, it indicates that the difference between the current rotation speed adjustment factor and the prediction result exceeds the acceptable range, and the rotation speed adjustment factor is small, and the rotation speed adjustment factor needs to be adjusted to ensure the stability of the motor rotation speed adjustment. Use the product value of the adjustment coefficient and the rotation speed adjustment factor as the target adjustment factor. When a larger target motor rotation speed is required, the rotation speed adjustment factor is adjusted by the adjustment coefficient, and the product value of the target adjustment factor and the motor rotation speed is determined as the target motor rotation speed, which improves the flexibility and dynamic adaptability of the adjustment.

[0085] In some embodiments of the present application, when preprocessing all infrared images, it includes: The preprocessing includes denoising and geometric correction. The warning unit uses the speeded-up robust features algorithm to extract feature points from all preprocessed infrared images, and matches the extracted feature points based on the random sample consensus algorithm to determine the matching information between each infrared image. Based on the matching information, all preprocessed infrared images are merged to determine the merged image, and the merged image is processed to determine the leakage image. The image processing includes removing the stitching seam and sharpening the image edge.

[0086] Specifically, denoising is achieved by using Gaussian filtering or median filtering. Geometric correction is used to correct the distortion in the image, ensuring the alignment between images, eliminating unnecessary information that affects subsequent processing, and improving the image quality. The Scale-invariant Feature Transform (SIFT) algorithm is used to extract feature points from all the preprocessed infrared images, and the Random Sample Consensus (RANSAC) algorithm is used to match the extracted feature points to determine the matching information between each pair of infrared images. The matching information represents the relative position and rotation relationship between the images. Based on affine transformation and perspective transformation, etc., multiple infrared images are registered to eliminate factors such as translation, rotation, and deformation caused by different shooting angles between the images, achieving precise alignment between the images. Then, according to algorithms such as weighted mean and multi-band fusion, the registered infrared images are merged to determine the merged image. After the merging is completed, image processing is performed on the merged image to determine the leakage image, so as to enhance the overall visual effect and stitching quality of the image. This lays a reliable foundation for the leakage warning of the pipeline.

[0087] In some embodiments of the present application, when determining the warning level according to the results of the preprocessing, it includes: the warning unit obtains the qualified pipeline images corresponding to the leakage images, extracts all the pixels to be detected in the leakage images, and extracts all the qualified pixels corresponding to the pixels to be detected from the qualified pipeline images. Determine the pixel values to be detected corresponding to all the pixels to be detected, determine the qualified pixel values corresponding to all the qualified pixels, count the number of pixels to be detected whose pixel values to be detected are not equal to the qualified pixel values, and preset a first preset number of pixels to be detected and a second preset number of pixels to be detected. The first preset number of pixels to be detected is greater than the second preset number of pixels to be detected. When the number of pixels to be detected is greater than or equal to the first preset number of pixels to be detected, the pipeline is determined to be in a first-level leakage warning. When the number of pixels to be detected is less than the first preset number of pixels to be detected and greater than the second preset number of pixels to be detected, the pipeline is determined to be in a second-level leakage warning. When the number of pixels to be detected is less than or equal to the second preset number of pixels to be detected, the pipeline is determined to be in a third-level leakage warning. The urgency of the first-level leakage warning, the second-level leakage warning, and the third-level leakage warning decreases in turn.

[0088] Specifically, by comparing the pixels to be detected in the leakage image with the corresponding qualified pixels in the qualified pipeline image, and using the number of pixels to be detected with pixel value differences as the judgment basis, a detailed and accurate quantitative assessment of the pipeline gas leakage situation can be carried out. The qualified pipeline image is obtained when there is no leakage in the pipeline. The pixels to be detected and the qualified pixels correspond one by one, ensuring the correspondence between the pixel values to be detected and the qualified pixel values. The difference in pixel values directly reflects the change in gas leakage in the pipeline. The more the number of pixels to be detected, the larger the range and degree of gas leakage, thus accurately judging the leakage situation of the pipeline. Dynamically determining the leakage warning based on the number of pixels to be detected improves the flexibility and dynamic adaptability of the detection warning, provides a strong reference basis for the maintenance and management of the pipeline, and further improves the safety and reliability of the pipeline.

[0089] In some embodiments of the present application, when determining the warning level according to the result of preprocessing, it includes: the warning unit obtains a qualified pipeline image corresponding to the leakage image, extracts all the pixels to be detected in the leakage image, and extracts all the qualified pixels corresponding to the pixels to be detected from the qualified pipeline image, determines the pixel values to be detected corresponding to all the pixels to be detected, determines the qualified pixel values corresponding to all the qualified pixels, counts the number of pixels to be detected whose pixel values to be detected are not equal to the qualified pixel values, and preset a first preset number of pixels to be detected and a second preset number of pixels to be detected, the first preset number of pixels to be detected is greater than the second preset number of pixels to be detected. When the number of pixels to be detected is greater than or equal to the first preset number of pixels to be detected, the pipeline is determined to be at the first-level leakage warning. When the number of pixels to be detected is less than the first preset number of pixels to be detected and greater than the second preset number of pixels to be detected, the pipeline is determined to be at the second-level leakage warning. When the number of pixels to be detected is less than or equal to the second preset number of pixels to be detected, the pipeline is determined to be at the third-level leakage warning. The emergency levels of the first-level leakage warning, the second-level leakage warning, and the third-level leakage warning decrease in sequence.

[0090] Specifically, by comparing the pixels to be detected in the leakage image with the corresponding qualified pixels in the qualified pipeline image, and using the number of pixels to be detected with pixel value differences as the judgment basis, a detailed and accurate quantitative assessment of the pipeline gas leakage situation can be carried out. The qualified pipeline image is obtained when there is no leakage in the pipeline. The pixels to be detected correspond one-to-one with the qualified pixels, ensuring the correspondence between the pixel values to be detected and the qualified pixel values. The difference in pixel values directly reflects the change of gas leakage in the pipeline. The more the number of pixels to be detected, the larger the range and degree of gas leakage, so as to accurately judge the leakage situation of the pipeline. Dynamically determining the leakage warning based on the number of pixels to be detected improves the flexibility and dynamic adaptability of the detection warning, provides a strong reference basis for the maintenance and management of the pipeline, and thus improves the safety and reliability of the pipeline.

[0091] In summary, the beneficial effects of the present invention are as follows: By adopting the internal detection technology, it can penetrate deep into the pipeline interior. Whether it is an above-ground pipeline or a buried pipeline, gas leakage detection can be carried out, effectively making up for the deficiencies of the external detection technology and expanding the applicable scope of detection, enabling the periscope infrared mechanism to perform multi-angle rotation adjustment. It can collect infrared light at different angles inside the pipeline in all directions, effectively expanding the imaging field of view, and can comprehensively detect each area inside the pipeline, so as to timely discover gas leakage points and issue corresponding warnings, ensuring the operation of the gas pipeline network and industrial transportation pipelines.

[0092] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0093] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0094] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the specific implementation manners of the present invention can still be modified or equivalently replaced, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. An active infrared optical detection device for gas leakage in a pipeline, characterized in that, Including: A detection body, which includes a driving motor, a motor fixing ring, a unidirectional rotation mechanism, a periscope infrared structure, an infrared camera structure, and a camera fixing base; The driving motor is connected to the unidirectional rotation mechanism. The driving motor is used to drive the unidirectional rotation mechanism, and the motor fixing ring is used to fix the driving motor; One end of the periscope infrared mechanism is connected to the unidirectional rotation mechanism, the other end of the periscope infrared mechanism is connected to the infrared camera mechanism, the bottom of the infrared camera mechanism is fixedly connected to the top of the camera fixing base, the driving motor is provided with a motor shaft, and the motor shaft penetrates through the motor fixing ring; The unidirectional rotation mechanism includes a rotation mechanism upper cover, a rotation mechanism lower cover, a rotation module, a slider, and a slider spring; The rotation mechanism upper cover is fixedly connected to the rotation mechanism lower cover. The rotation module is arranged inside the enclosed space formed by the rotation mechanism upper cover and the rotation mechanism lower cover. A plurality of slider springs are provided, and a plurality of sliders are provided. Each slider spring is fixedly connected to the side wall of the rotation mechanism lower cover, and each slider spring is fixedly connected to a slider; The rotation module includes a rotation shaft, a lever spring, a lever, a unidirectional rotation turntable, and a groove; The motor shaft sleeves the rotation shaft. The rotation shaft is engaged with the unidirectional rotation turntable. The unidirectional rotation turntable is provided with the groove. The rotation shaft is fixedly connected to the lever. One end of the lever spring is fixedly connected to the lever, and the other end of the lever spring is fixedly connected to the unidirectional rotation turntable.

2. The active infrared optical detection device for gas leakage in a pipeline according to claim 1, wherein It also includes: The periscope infrared mechanism includes a periscope infrared body and a vertical reflector; The vertical reflector is arranged inside the periscope infrared body; The periscope infrared body includes a periscope structure housing, an infrared light source, an infrared light homogenizing plate, a single-sided concave lens, and a single-sided convex lens; The infrared light source is arranged inside the periscope structure housing. The infrared light homogenizing plate is attached to the infrared light source. The single-sided concave lens and the single-sided convex lens are arranged inside the periscope structure housing; The infrared camera structure is provided with a data output serial port; A control module, which is electrically connected to the driving motor, the periscope infrared structure, and the infrared camera structure. The control module is used to control the working states of the driving motor and the periscope infrared structure.

3. The active infrared optical detection device for gas leakage in a pipeline according to claim 2, characterized in that, The control module includes: An acquisition unit, configured to acquire the current infrared image at the current moment inside the pipeline and the previous infrared image at the same angle at the previous moment; A judgment unit, configured to compare the current infrared image with the previous infrared image, judge whether to adjust the motor speed of the driving motor according to the comparison result, and when it is determined that adjustment is required, determine a speed adjustment factor based on the current infrared image and the previous infrared image; A processing unit, configured to obtain a rotational speed data set, determine a rotational speed prediction adjustment factor based on the rotational speed data set and a rotational speed model, determine a factor deviation value according to the rotational speed adjustment factor and the rotational speed prediction adjustment factor, when the factor deviation value is less than a factor deviation threshold, obtain all historical motor rotational speeds, analyze all historical motor rotational speeds, determine an adjustment coefficient of the rotational speed adjustment factor based on the analysis result, and adjust the rotational speed adjustment factor based on the adjustment coefficient to determine a target motor rotational speed; An early warning unit, configured to obtain infrared images at at least three angles based on the target motor rotational speed, preprocess all the infrared images, and determine an early warning level according to the result of the preprocessing.

4. The active infrared optical detection device for gas leakage in a pipeline according to claim 3, characterized in that, When judging whether to adjust the motor rotational speed of the drive motor according to the comparison result, it includes: If the pixel points of the current infrared image are the same as those of the previous infrared image, the judging unit determines not to adjust the motor rotational speed; If the pixel points of the current infrared image are different from those of the previous infrared image, the judging unit determines to adjust the motor rotational speed.

5. The active infrared optical detection device for gas leakage in a pipeline according to claim 4, characterized in that, When determining the rotational speed adjustment factor based on the current infrared image and the previous infrared image, it includes: The judging unit extracts the different pixel points of the current infrared image and the previous infrared image, and counts the number of differences of the different pixel points; A first preset difference quantity and a second preset difference quantity are preset in advance, and the first preset difference quantity is greater than the second preset difference quantity; When the number of differences is greater than or equal to the first preset difference quantity, the first rotational speed coefficient is used as the rotational speed adjustment factor; When the number of differences is less than the first preset difference quantity and greater than the second preset difference quantity, the second rotational speed coefficient is used as the rotational speed adjustment factor; When the number of differences is less than or equal to the second preset difference quantity, the third rotational speed coefficient is used as the rotational speed adjustment factor; Wherein, the value range of the rotational speed coefficient is: 1 < the third rotational speed coefficient < the second rotational speed coefficient < the first rotational speed coefficient.

6. The active infrared optical detection device for gas leakage in a pipeline according to claim 5, characterized in that, When determining the rotational speed prediction adjustment factor based on the rotational speed data set and the rotational speed model, it includes: The processing unit divides the rotational speed data set into a training set and a test set, uses grid search to find hyperparameters to establish a decision tree model, fits the decision tree model according to the training set, and substitutes the test set into the decision tree model for evaluation; When the evaluation value reaches a preset evaluation threshold, the rotational speed prediction adjustment factor is determined according to the number of differences.

7. The active infrared optical detection device for gas leakage in a pipeline according to claim 6, characterized in that, When determining the factor deviation value according to the rotational speed adjustment factor and the rotational speed prediction adjustment factor, it includes: The processing unit determines the ratio of the rotational speed adjustment factor and the rotational speed prediction adjustment factor as the factor deviation value, and presets the factor deviation threshold; When the factor deviation value is greater than or equal to the factor deviation threshold, it is determined not to adjust the rotational speed adjustment factor, and the product value of the rotational speed adjustment factor and the motor rotational speed is determined as the target motor rotational speed; When the factor deviation value is less than the factor deviation threshold, it is determined to adjust the rotational speed adjustment factor.

8. The active infrared optical detection device for gas leakage in a pipeline according to claim 7, wherein When determining the adjustment coefficient of the rotational speed adjustment factor based on the analysis result, and adjusting the rotational speed adjustment factor based on the adjustment coefficient to determine the target motor speed, it includes: The processing unit analyzes all historical motor speeds, determines the overclocking speed, default speed, and low-frequency speed, constructs all overclocking speeds into a first historical speed set, constructs all low-frequency speeds into a second historical speed set, obtains the first speed average value in the first historical speed set, and obtains the second speed average value in the second historical speed set; Obtain the first difference between the first speed average value and the default speed, and obtain the second difference between the default speed and the second speed average value, obtain the absolute value of the ratio of the first difference to the second difference, and use the absolute value as the adjustment coefficient; Take the product value of the adjustment coefficient and the rotational speed adjustment factor as the target adjustment factor, and determine the product value of the target adjustment factor and the motor speed as the target motor speed.

9. The active infrared optical detection device for gas leakage in a pipeline according to claim 8, characterized in that, When preprocessing all infrared images, it includes: The preprocessing includes denoising and geometric correction. The warning unit uses the speeded up robust features (SURF) algorithm to extract feature points from all preprocessed infrared images, and matches the extracted feature points based on the random sample consensus (RANSAC) algorithm to determine the matching information between each infrared image, and merges all preprocessed infrared images based on the matching information to determine the merged image; Perform image processing on the merged image to determine the leakage image, and the image processing includes removing the stitching seam and sharpening the image edge.

10. The active infrared optical detection device for gas leakage in a pipeline according to claim 9, characterized in that, When determining the warning level according to the result of the preprocessing, it includes: The warning unit obtains the qualified pipeline image corresponding to the leakage image; Extract all pixels to be detected in the leakage image, and extract all qualified pixels corresponding to the pixels to be detected from the qualified pipeline image, determine the pixel values to be detected corresponding to all pixels to be detected, and determine the qualified pixel values corresponding to all qualified pixels; Count the number of pixels to be detected whose pixel values to be detected are not equal to the qualified pixel values, and preset a first preset number of pixels to be detected and a second preset number of pixels to be detected, where the first preset number of pixels to be detected is greater than the second preset number of pixels to be detected; When the number of pixels to be detected is greater than or equal to the first preset number of pixels to be detected, determine that the pipeline has a first-level leakage warning; When the number of pixels to be detected is less than the first preset number of pixels to be detected and greater than the second preset number of pixels to be detected, determine that the pipeline has a second-level leakage warning; When the number of pixels to be detected is less than or equal to the second preset number of pixels to be detected, determine that the pipeline has a third-level leakage warning; The emergency levels of the first-level leakage warning, second-level leakage warning, and third-level leakage warning decrease in sequence.

Images