Carbon emission monitoring system based on petroleum and natural gas industry

Abstract

The invention relates to the field of cloud platform carbon emission monitoring, in particular to a petroleum and natural gas industry-based carbon emission monitoring system, which is provided with a data acquisition module, a cloud platform analysis module, a touch trigger module and a prediction module, the diffusion characteristics and the offset characteristics are analyzed through the cloud platform analysis module, the diffusion abnormal tendency is judged through the touch trigger module, the sampling frequency of the data acquisition module in the supervision area is adjusted through the trigger adjustment module, and the diffusion condition of the current monitoring target is predicted through the prediction module. And judging whether the current monitoring target has abnormal emission or not, determining potential abnormal diffusion tendency by adopting an attention mechanism and diffusion characteristics through the process, performing subsequent high-frequency sampling, analyzing whether the emission is abnormal or not by adopting a prediction form according to the sampled data, and reducing the data analysis quantity on the premise of monitoring a large-area region and ensuring the reliability. And the accuracy of carbon emission monitoring is ensured.

Description

Technical Field

[0001] The present invention relates to the field of carbon emission monitoring, and particularly to a carbon emission monitoring system based on the oil and gas industry. Background Art

[0002] With the development of Internet technology, various data control and monitoring systems based on cloud platforms have emerged. The cloud platform can be used to obtain and then analyze the data to be monitored in the target area. In the oil and gas field, due to actual production needs, relevant industrial parks are the main sources of volatile organic compound emissions. With climate change and people's concern about carbon emission reduction, the development and application of efficient carbon emission detection technologies are crucial, which helps to reduce carbon emissions and protect the environment.

[0003] For example, Chinese Patent Publication No.: CN118865635A discloses a method and device for warning of oil and gas based on carbon emission control. The carbon emission terminals of the oil and gas to be warned are marked with network elements, and multiple oil and gas carbon emission warning network elements and network element data sets are output; an oil and gas carbon emission prediction network is constructed, and infrared detection is performed on multiple oil and gas carbon emission warning network elements, and the sensor detection result sets of each network element are output; according to the synchronous interaction strategy, the completion degree synchronization of the sensor detection result sets of the target oil and gas carbon emissions between two network elements among multiple oil and gas carbon emission warning network elements is performed, and the first propagation footprint of the target oil and gas carbon emissions is output and merged and evaluated, and the second propagation footprint of the target oil and gas carbon emissions is output. This invention optimizes the panoramic footprint based on the merging process, and uses the light intensity calculation and historical footprint information to complete the prediction and evaluation of the oil and gas carbon emissions, improving the robustness of the panoramic footprint and reducing the dependence on hardware.

[0004] However, the following problems still exist in the prior art.

[0005] When detecting emission sources in a large area, the method of sensor coverage is adopted, which requires processing a large amount of data, consumes a large amount of computing power, and is insensitive to the detection of some illegal carbon emissions. Summary of the Invention

[0006] Therefore, the present invention provides a carbon emission monitoring system based on the oil and gas industry to solve the problems that when monitoring emission sources in a large area, the method of sensor coverage requires processing a large amount of data, consumes a large amount of computing power, and is insensitive to the detection of some illegal carbon emissions.

[0007] To achieve the above object, the present invention provides a carbon emission monitoring system based on the oil and gas industry, which includes:

[0008] A data acquisition module, which includes a number of image acquisition units for acquiring images of each supervision area and an environmental wind characteristic acquisition unit for acquiring the wind direction and wind speed of each supervision area;

[0009] A cloud platform analysis module, which is connected to the data acquisition module, and is used to determine the monitoring target contour based on the supervision area image every predetermined period, analyze the diffusion characteristics, and determine the offset characteristics of the diffusion characteristics at the current temperature;

[0010] A sensitive trigger module, which is connected to the cloud platform analysis module, and is used to determine the diffusion anomaly tendency characterization parameter based on the offset amount of the diffusion characteristics and judge the diffusion anomaly tendency;

[0011] A trigger adjustment module, which is respectively connected to the data acquisition module and the sensitive trigger module, and in response to the judgment result of the sensitive trigger module, is used to adjust the acquisition frequency of the data acquisition module in the corresponding supervision area according to the diffusion anomaly characterization parameter;

[0012] A prediction module, which is respectively connected to the data acquisition module and the trigger adjustment module, and is used to obtain the data of the data acquisition module, predict the diffusion situation of the current monitoring target, determine the predicted distribution map of the smoke diffusion, compare it with the smoke contour in the actual supervision area image, and judge whether there is an emission anomaly in the current supervision area according to the comparison result;

[0013] Wherein, the diffusion flow characteristics include diffusion speed, diffusion contour blur degree and diffusion gradient.

[0014] Further, the cloud platform analysis module is used to analyze the diffusion characteristics including,

[0015] Used to identify the smoke contour in the supervision area image;

[0016] Used to determine a number of feature points in the smoke contour, analyze the average displacement of each feature point in the continuous image sequence, and determine the diffusion speed;

[0017] Used to reduce the smoke contour by a predetermined ratio to construct a reference contour, determine a number of image blocks in the area formed by the reference contour and the smoke contour, calculate the spectrum energy representation of each image block by Fourier transform, determine the high-frequency energy ratio of each image block, and determine the high-frequency energy ratio as the diffusion contour blur degree;

[0018] Used to determine the center of the smoke contour, construct a number of equally angled rays with the center of the smoke contour as the center, determine a number of observation points along the rays, determine the corresponding gray values of the observation points, obtain the gray gradient difference for a single ray, and determine the average value of the gray gradient differences corresponding to each ray as the diffusion gradient.

[0019] Further, the offset characteristics of the diffusion characteristics determined by the cloud platform analysis module include

[0020] to determine the reference diffusion speed, reference diffusion profile blur degree, and reference diffusion gradient at the current temperature;

[0021] to calculate the diffusion speed difference ratio between the diffusion speed and the reference diffusion speed;

[0022] to calculate the diffusion profile blur degree difference ratio between the diffusion profile blur degree and the reference diffusion profile blur degree;

[0023] to calculate the diffusion gradient difference ratio between the diffusion gradient and the reference diffusion gradient;

[0024] wherein, the cloud platform analysis module pre-stores the corresponding reference diffusion characteristics in different temperature ranges.

[0025] Further, the sensitive trigger module determines the diffusion anomaly tendency characterization parameter including

[0026] to perform a weighted sum of the diffusion speed difference ratio, diffusion profile blur degree difference ratio, and diffusion gradient difference ratio to obtain the diffusion anomaly tendency characterization parameter.

[0027] Further, the sensitive trigger module determines the diffusion anomaly tendency based on the comparison result between the diffusion anomaly tendency characterization parameter and the preset standard threshold of the diffusion anomaly tendency characterization parameter, including

[0028] If the diffusion anomaly tendency characterization parameter is greater than or equal to the preset standard threshold of the diffusion anomaly tendency characterization parameter, the sensitive trigger module determines that there is a diffusion anomaly tendency in the supervision area;

[0029] If the diffusion anomaly characterization parameter is less than the preset standard threshold of the diffusion anomaly tendency characterization parameter, the sensitive trigger module determines that there is no abnormal emission tendency in the supervision area.

[0030] Further, the trigger adjustment module responds to the determination result of the sensitive trigger module, including

[0031] If it is determined that there is a diffusion anomaly tendency in the supervision area, the trigger adjustment module starts to respond and adjusts the acquisition frequency of the data acquisition module in the corresponding supervision area according to the diffusion anomaly characterization parameter.

[0032] Further, the trigger adjustment module adjusts the acquisition frequency of the data acquisition module based on the diffusion anomaly characterization parameter, wherein

[0033] the acquisition frequency is positively correlated with the diffusion anomaly characterization parameter.

[0034] Further, the prediction module is used to predict the diffusion of the current monitoring target, including

[0035] extracting a number of smoke points in the image of the supervision area and determining the environmental wind direction as the diffusion direction;

[0036] obtaining the corresponding reference diffusion speed at the current wind speed;

[0037] predicting the diffusion positions of each peripheral smoke point after a predetermined time according to the diffusion direction and the reference diffusion speed;

[0038] marking the diffused peripheral smoke points in the supervision area image and connecting the peripheral smoke points to obtain a predicted distribution map of the smoke diffusion situation;

[0039] repeatedly obtaining the predicted distribution maps of the smoke diffusion situation at different time nodes and synchronously recording the images of the supervision area at the corresponding time nodes.

[0040] Further, the prediction module is used to compare the predicted distribution map of the smoke diffusion situation with the smoke contour in the actual supervision area image, including

[0041] comparing the area difference between the corresponding area of the predicted distribution map of the smoke diffusion situation and the actual area corresponding to the smoke contour at different time nodes, and solving the average value of the area differences.

[0042] Further, the prediction module determines whether there is an abnormal emission of the current monitoring target according to the comparison result, including

[0043] comparing the average value of the area differences with a preset area difference comparison threshold. If the average value of the area differences is greater than or equal to the preset area difference comparison threshold, it is determined that there is an abnormal emission in the current supervision area.

[0044] Compared with the prior art, the present invention sets up a data acquisition module, a cloud platform analysis module, a touch trigger module and a prediction module. The data acquisition module collects the image of the supervision area, the cloud platform analysis module determines the contour of the monitoring target, analyzes the diffusion characteristics, and determines the offset characteristics of the diffusion characteristics at the current temperature. The touch trigger module determines the characteristic parameters of the diffusion anomaly tendency and judges the diffusion anomaly tendency. The trigger adjustment module adjusts the sampling frequency of the data acquisition module in the supervision area. The prediction module predicts the diffusion situation of the current monitoring target, determines the diffusion ratio time-domain curve based on the prediction result, and judges whether there is an abnormal emission of the current monitoring target. Through the above process, the attention mechanism is adopted to determine the potential diffusion anomaly tendency through the diffusion characteristics, and subsequent high-frequency sampling is carried out. Whether the emission is abnormal is analyzed in a predictive form based on the sampling data. When monitoring a large area, the amount of data analysis is reduced on the premise of ensuring reliability, and the accuracy of carbon emission monitoring is guaranteed.

[0045] In particular, the present invention considers analyzing the diffusion characteristics of the monitored target contour. In actual situations, when some emission sources violate carbon emissions, due to differences in the emitted gases, the properties of gas molecules affect the diffusion of the gas, and thus the gas diffusion shows differences. This difference can be characterized in the image, and thus large-area monitoring can be achieved through the image. The mixing of illegal gases or the violation of the emission volume in the emission source will affect the diffusion speed after emission. For gases with different concentrations, their tendency to blend with the environment is different, and thus the data representativeness of the diffusion contour clarity is relatively strong. Moreover, for different gases, due to different molecular thermal motions under the influence of temperature, there are also differences in the diffusion gradient during the diffusion process. Therefore, the invention considers the diffusion characteristics, and thus high-precision images can be used to periodically collect images of the supervised area. The image acquisition method takes into account large-area supervision, and it is convenient to identify abnormal carbon emissions in the supervised area later, ensuring the accuracy of carbon emission monitoring.

[0046] In particular, the present invention calculates the diffusion anomaly tendency characterization parameter to determine the diffusion anomaly tendency. In actual situations, the diffusion characteristics have data representativeness and can be collected through images, and thus are applicable to large-area monitoring. The present invention conducts periodic monitoring to more sensitively identify the supervised areas with a diffusion anomaly tendency, and then adjusts the sampling frequency of the image acquisition unit in this area later. The prediction method is used to predict the predicted distribution map of the smoke diffusion under normal circumstances, and then it is compared with the actual situation later to obtain the average area difference, which can more comprehensively reflect the difference between the actual diffusion situation and the diffusion situation under normal circumstances, and then identify whether there is an abnormality in the emission later. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic structural diagram of the carbon emission monitoring system based on the oil and gas industry according to an embodiment of the invention;

[0048] Figure 2 It is a logic block diagram for determining the abnormal emission tendency according to an embodiment of the invention;

[0049] Figure 3 It is a logic block diagram for the trigger adjustment module to respond to the determination result of the sensitive trigger module according to an embodiment of the invention;

[0050] Figure 4 It is a logic block diagram for determining whether there is an emission abnormality in the current monitored target according to an embodiment of the invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] In order to make the objectives and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principle of the present invention and do not limit the protection scope of the present invention.

[0053] It should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0054] Please refer to Figures 1 to 4 as shown Figure 1 which is a schematic structural diagram of the carbon emission monitoring system based on the oil and gas industry according to an embodiment of the invention, Figure 2 which is a logic block diagram for determining the abnormal emission tendency according to an embodiment of the invention, Figure 3 which is a logic block diagram for the trigger adjustment module to respond to the determination result of the sensitive trigger module according to an embodiment of the invention, Figure 4 which is a logic block diagram for determining whether there is an abnormal emission in the current monitoring target according to an embodiment of the invention. The carbon emission monitoring system based on the oil and gas industry of the present invention includes:

[0055] A data acquisition module, which includes a plurality of image acquisition units for acquiring images of each supervision area and an environmental wind characteristic acquisition unit for acquiring the wind direction and wind speed of each supervision area;

[0056] A cloud platform analysis module, which is connected to the data acquisition module and is used to determine the monitoring target contour based on the supervision area image every predetermined period, analyze the diffusion characteristics, and determine the offset characteristics of the diffusion characteristics at the current temperature;

[0057] A sensitive trigger module, which is connected to the cloud platform analysis module and is used to determine the diffusion abnormal tendency characterization parameter based on the offset amount of the diffusion characteristics and determine the diffusion abnormal tendency;

[0058] A trigger adjustment module, which is respectively connected to the data acquisition module and the sensitive trigger module, responds to the determination result of the sensitive trigger module, and is used to adjust the acquisition frequency of the data acquisition module in the corresponding supervision area according to the diffusion abnormal characterization parameter;

[0059] A prediction module, which is respectively connected to the data acquisition module and the trigger adjustment module, is used to obtain the data of the data acquisition module, predict the diffusion situation of the current monitoring target, determine the predicted distribution map of the smoke diffusion situation, compare it with the smoke contour in the actual supervision area image, and determine whether there is an abnormal emission in the current supervision area according to the comparison result;

[0060] Among them, the diffusion flow characteristics include diffusion speed, diffusion contour blur degree, and diffusion gradient.

[0061] Specifically, the specific form of the image acquisition unit is not limited. It can be a high-definition camera carried by a drone or multiple high-position monitoring high-definition cameras set in the supervision area, as long as it can monitor the supervision area and transmit back pictures to meet the data analysis requirements, which will not be elaborated here.

[0062] Specifically, the environmental wind characteristic acquisition unit can adopt any one of the existing sensors, as long as it can obtain the environmental wind speed and environmental wind direction. Those skilled in the art can select according to specific needs.

[0063] Specifically, the specific structures of the cloud platform analysis module, the sensitive trigger module, the trigger adjustment module, and the prediction module are not limited. They can be composed of logic components, and the logic components include a field programmable processor, a computer, or a microprocessor in the computer.

[0064] Specifically, the cloud platform analysis module is used to extract the diffusion flow characteristics, including

[0065] being used to identify the smoke contour in the supervision area image;

[0066] being used to determine several feature points in the smoke contour, analyze the average displacement of each of the feature points in the continuous image sequence, and determine the diffusion speed;

[0067] being used to reduce the smoke contour by a predetermined ratio to construct a reference contour, determine several image blocks in the area formed by the reference contour and the smoke contour, calculate the spectral energy representation for each image block, determine the high-frequency energy ratio of each image block, and determine the high-frequency energy ratio as the diffusion contour blur degree;

[0068] It can be understood that for the spectral energy signature after Fourier transform, the low-frequency energy is concentrated in the center of the spectrum, and the high-frequency energy is concentrated on the periphery of the spectrum. Those skilled in the art can determine the energy outside a predetermined distance from the center of the spectrum as the high-frequency energy. The predetermined distance can be defined according to the total distance of the spectral energy representation, usually set between 50% and 80% of the total distance.

[0069] To determine the center of the smoke contour, construct a number of rays with equal included angles based on the center of the smoke contour, determine a number of observation points along the rays, determine the corresponding gray values of the observation points, obtain the gray gradient difference for a single ray, and determine the mean value of the gray gradient differences corresponding to each ray as the diffusion gradient.

[0070] It can be understood that for the gray gradient difference of a single ray, the average difference between a single observation point and its adjacent observation points can be calculated respectively, and the mean value of the average differences for each observation point can be solved to obtain the gray gradient difference.

[0071] Specifically, there is no limitation on the specific method for identifying the smoke contour. For example, YOLO series algorithms, image segmentation algorithms. Of course, other methods can also be used. Those skilled in the art can select according to specific requirements or train relevant image recognition models by themselves to achieve the corresponding functions, which will not be elaborated here.

[0072] Specifically, the offset features of the diffusion features determined by the cloud platform analysis module at the current temperature include,

[0073] To determine the reference diffusion speed, reference diffusion contour blur degree, and reference diffusion gradient at the current temperature;

[0074] To calculate the diffusion speed difference ratio between the diffusion speed and the reference diffusion speed;

[0075] To calculate the diffusion contour blur degree difference ratio between the diffusion contour blur degree and the reference diffusion contour blur degree;

[0076] To calculate the diffusion gradient difference ratio between the diffusion gradient and the reference diffusion gradient;

[0077] Among them, the reference diffusion features corresponding to different temperature ranges are pre-stored in the cloud platform analysis module.

[0078] Specifically, the reference diffusion features for different temperature ranges are obtained by pre-detection. The diffusion sources in each detection area are tested in advance, the images of the supervised area in different temperature ranges under normal emissions are collected, and the diffusion features are extracted. After multiple detections, the mean values of the diffusion features in different temperature ranges are solved. The mean value of the diffusion speed is set as the reference diffusion speed, the mean value of the diffusion contour blur degree is set as the reference diffusion contour blur degree, and the mean value of the diffusion gradient is set as the reference diffusion gradient.

[0079] The present invention considers analyzing the diffusion characteristics of the monitored target contour. In actual situations, when some emission sources violate carbon emissions regulations, due to differences in the emitted gases, the properties of gas molecules affect the diffusion of the gas, and thus the gas diffusion shows differences. This kind of difference can be characterized in the image, and thus large-area monitoring can be achieved through the image. If the emission source is mixed with illegal gases or the emission volume violates the regulations, it will affect the diffusion speed after emission. For gases with different concentrations, their tendencies to blend with the environment are different, and thus the data representativeness in terms of the clarity of the diffusion contour is relatively strong. Moreover, for different gases, due to different molecular thermal motions under the influence of temperature, there are also differences in the diffusion gradient during the diffusion process. Therefore, the invention considers the diffusion characteristics, and through high-precision images, it can periodically collect images of the supervised area, adopt an image acquisition method that takes into account large-area supervision, and is convenient for identifying abnormal carbon emissions in the supervised area later, ensuring the accuracy of carbon emission monitoring.

[0080] Specifically, the sensitive trigger module determines that the diffusion anomaly tendency characterization parameter includes

[0081] used to perform a weighted sum of the diffusion speed difference ratio, the diffusion contour blur degree difference ratio, and the diffusion gradient difference ratio to obtain the diffusion anomaly tendency characterization parameter.

[0082] In implementation, the weight of the diffusion speed difference ratio is 0.3, the weight of the diffusion contour blur degree difference ratio is 0.4, and the weight of the diffusion gradient difference ratio is 0.3.

[0083] Specifically, the sensitive trigger module determines the diffusion anomaly tendency based on the comparison result between the diffusion anomaly tendency characterization parameter and the preset standard threshold of the diffusion anomaly tendency characterization parameter, including

[0084] If the diffusion anomaly tendency characterization parameter is greater than or equal to the preset standard threshold of the diffusion anomaly tendency characterization parameter, the sensitive trigger module determines that there is a diffusion anomaly tendency in the supervised area;

[0085] If the diffusion anomaly characterization parameter is less than the preset standard threshold of the diffusion anomaly tendency characterization parameter, the sensitive trigger module determines that there is no abnormal emission tendency in the supervised area.

[0086] In implementation, the standard threshold of the diffusion anomaly tendency characterization parameter is selected within the interval [0.15, 0.3].

[0087] Specifically, the trigger adjustment module responds to the determination result of the sensitive trigger module, including

[0088] If it is determined that there is a diffusion anomaly tendency in the supervised area, the trigger adjustment module starts to respond and adjusts the acquisition frequency of the data acquisition module in the corresponding supervised area according to the diffusion anomaly characterization parameter.

[0089] Specifically, the trigger adjustment module adjusts the acquisition frequency of the data acquisition module based on the diffusion anomaly characterization parameter, where

[0090] the acquisition frequency is positively correlated with the diffusion anomaly characterization parameter;

[0091] Optionally, the acquisition frequency is determined according to the following formula

[0092]

[0093] In the formula, Be represents the acquisition frequency, g represents the offset coefficient, A represents the diffusion anomaly tendency characterization parameter, A0 represents the standard threshold of the diffusion anomaly tendency characterization parameter, B represents the reference acquisition frequency, and 1.1 < g < 1.3.

[0094] In the case of no anomaly, the acquisition frequency is the reference acquisition frequency.

[0095] It can be understood that the acquisition frequency is for the image acquisition unit and the environmental wind feature acquisition unit. Each unit has a corresponding reference acquisition frequency, and the acquisition frequency of each unit can be determined based on the above formula, which will not be elaborated here.

[0096] Specifically, the prediction module is used to predict the diffusion of the current monitoring target, including

[0097] extracting several smoke points in the image of the supervised area and determining the environmental wind direction as the diffusion direction;

[0098] obtaining the corresponding reference diffusion speed at the current wind speed;

[0099] predicting the diffusion positions of each peripheral smoke point after a predetermined time according to the diffusion direction and the reference diffusion speed. It can be understood that in actual situations, appropriate compensation can be made to the diffusion direction. Considering that gas naturally rises, the diffusion direction can be offset perpendicular to the ground for compensation. The specific compensation amount can be specifically set by those skilled in the art, which will not be elaborated here.

[0100] marking the diffused peripheral smoke points in the image of the supervised area and connecting the peripheral smoke points to obtain a predicted distribution map of the smoke diffusion situation;

[0101] repeatedly obtaining the predicted distribution maps of the smoke diffusion situation at different time nodes and synchronously recording the images of the supervised area at the corresponding time nodes.

[0102] Specifically, the prediction module is used to compare the predicted distribution map of the smoke diffusion situation with the smoke contour in the actual image of the supervised area, including

[0103] To compare the area difference between the predicted distribution map of the smoke diffusion situation at different time nodes and the actual area corresponding to the smoke contour, and solve the average value of the area difference.

[0104] Specifically, the prediction module determines whether there is an abnormal emission in the current monitoring target based on the comparison result, including

[0105] Compare the average value of the area difference with a preset area difference comparison threshold. If the average value of the area difference is greater than or equal to the preset area difference comparison threshold, it is determined that there is an abnormal emission in the current supervision area.

[0106] Specifically, the area difference comparison threshold is determined based on the area of the smoke contour in the supervision area image at the moment when the trigger adjustment module responds, and is set between 0.1 times and 0.3 times of the area.

[0107] The present invention calculates the diffusion anomaly tendency characterization parameter and determines the diffusion anomaly tendency. In actual situations, the diffusion characteristics have data representativeness and can be collected through images, so it is applicable to large-area monitoring. The present invention conducts monitoring periodically, and can more sensitively identify the supervision area with the tendency of diffusion anomaly, and then adjust the sampling frequency of the image acquisition unit in this area subsequently. The predicted distribution map of the smoke diffusion situation under normal conditions is predicted in a predictive manner, and then compared with the actual situation subsequently to obtain the average value of the area difference, which can more comprehensively reflect the difference between the actual diffusion situation and the diffusion situation under normal conditions, and then identify whether there is an abnormal emission subsequently.

[0108] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

Claims

1. A carbon emission monitoring system based on the oil and gas industry, characterized in that, Including: A data acquisition module, which includes several image acquisition units for acquiring images of each supervision area and an environmental wind characteristic acquisition unit for acquiring the wind direction and wind speed of each supervision area; A cloud platform analysis module, which is connected to the data acquisition module, and is used to determine the monitoring target contour based on the supervision area image every predetermined period, analyze the diffusion characteristics, and determine the offset characteristics of the diffusion characteristics at the current temperature; A sensitive trigger module, which is connected to the cloud platform analysis module, and is used to determine the diffusion anomaly tendency characterization parameter based on the offset amount of the diffusion characteristics and judge the diffusion anomaly tendency; A trigger adjustment module, which is respectively connected to the data acquisition module and the sensitive trigger module, and responds to the judgment result of the sensitive trigger module, and is used to adjust the acquisition frequency of the data acquisition module in the corresponding supervision area according to the diffusion anomaly characterization parameter; A prediction module, which is respectively connected to the data acquisition module and the trigger adjustment module, and is used to obtain the data of the data acquisition module, predict the diffusion situation of the current monitoring target, determine the predicted distribution map of the smoke diffusion situation, compare it with the smoke contour in the actual supervision area image, and judge whether there is an emission anomaly in the current supervision area according to the comparison result; Wherein, the diffusion flow characteristics include diffusion speed, diffusion contour blur degree, and diffusion gradient.

2. The carbon emission monitoring system based on the oil and gas industry according to claim 1, wherein The cloud platform analysis module is used to analyze the diffusion characteristics, including: Used to identify the smoke contour in the supervision area image; Used to determine several feature points in the smoke contour, analyze the average displacement amount of each feature point in the continuous image sequence, and determine the diffusion speed; Used to reduce the smoke contour by a predetermined ratio to construct a reference contour, determine several image blocks in the area formed by the reference contour and the smoke contour, perform Fourier transform on each image block to calculate the spectrum energy representation, determine the high-frequency energy ratio of each image block, and determine the high-frequency energy ratio as the diffusion contour blur degree; Used to determine the center of the smoke contour, construct several rays with equal included angles with the center of the smoke contour, determine several observation points along the rays, determine the corresponding gray values of the observation points, obtain the gray gradient difference for a single ray, and determine the average value of the gray gradient differences corresponding to each ray as the diffusion gradient.

3. The carbon emission monitoring system based on the oil and gas industry according to claim 2, characterized in that, The cloud platform analysis module determines the offset characteristics of the diffusion characteristics at the current temperature, including: Used to determine the reference diffusion speed, reference diffusion contour blur degree, and reference diffusion gradient at the current temperature; Used to calculate the diffusion speed difference ratio between the diffusion speed and the reference diffusion speed; Used to calculate the diffusion contour blur degree difference ratio between the diffusion contour blur degree and the reference diffusion contour blur degree; Used to calculate the diffusion gradient difference ratio between the diffusion gradient and the reference diffusion gradient; Wherein, the cloud platform analysis module pre-stores the corresponding reference diffusion characteristics in different temperature ranges.

4. The carbon emission monitoring system based on the oil and gas industry according to claim 3, wherein The sensitive trigger module determines the diffusion anomaly tendency characterization parameter, including: Used to weight and sum the diffusion speed difference ratio, diffusion contour blur degree difference ratio, and diffusion gradient difference ratio to obtain the diffusion anomaly tendency characterization parameter.

5. The carbon emission monitoring system based on the oil and gas industry according to claim 1, characterized in that, The sensitive trigger module determines the diffusion anomaly tendency based on the comparison result between the diffusion anomaly tendency characterization parameter and the preset standard threshold of the diffusion anomaly tendency characterization parameter. including If the diffusion anomaly tendency characterization parameter is greater than or equal to the preset standard threshold of the diffusion anomaly tendency characterization parameter, the sensitive trigger module determines that there is a diffusion anomaly tendency in the supervision area. If the diffusion anomaly characterization parameter is less than the preset standard threshold of the diffusion anomaly tendency characterization parameter, the sensitive trigger module determines that there is no abnormal emission tendency in the supervision area.

6. The carbon emission monitoring system based on the oil and gas industry according to claim 1, characterized in that, The trigger adjustment module responds to the determination result of the sensitive trigger module, including If it is determined that there is a diffusion anomaly tendency in the supervision area, the trigger adjustment module starts to respond and adjusts the acquisition frequency of the data acquisition module in the corresponding supervision area according to the diffusion anomaly characterization parameter.

7. The carbon emission monitoring system based on the oil and gas industry according to claim 1, characterized in that, The trigger adjustment module adjusts the acquisition frequency of the data acquisition module based on the diffusion anomaly characterization parameter, where The acquisition frequency is positively correlated with the diffusion anomaly characterization parameter.

8. The carbon emission monitoring system based on the oil and gas industry according to claim 1, wherein The prediction module is used to predict the diffusion of the current monitoring target, including extracting several smoke points in the supervision area image and determining the environmental wind direction as the diffusion direction; obtaining the corresponding reference diffusion speed at the current wind speed; predicting the diffusion positions of each peripheral smoke point after a predetermined time according to the diffusion direction and the reference diffusion speed; marking the diffused peripheral smoke points in the supervision area image and connecting the peripheral smoke points to obtain a predicted distribution map of the smoke diffusion situation; repeating to obtain the predicted distribution maps of the smoke diffusion situation at different time nodes and synchronously recording the supervision area images corresponding to the time nodes.

9. The carbon emission monitoring system based on the oil and gas industry according to claim 1, wherein The prediction module is used to compare the predicted distribution map of the smoke diffusion situation with the smoke contour in the actual supervision area image, including comparing the area difference between the corresponding area of the predicted distribution map of the smoke diffusion situation and the actual area of the smoke contour at different time nodes, and solving the average value of the area difference.

10. The carbon emission monitoring system based on the oil and gas industry according to claim 9, characterized in that, The prediction module determines whether there is an emission anomaly in the current monitoring target according to the comparison result, including comparing the average value of the area difference with the preset area difference comparison threshold. If the average value of the area difference is greater than or equal to the preset area difference comparison threshold, it is determined that there is an emission anomaly in the current supervision area.

Images