Unmanned aerial vehicle inspection system for oil and gas station

Abstract

The invention belongs to the technical field of unmanned aerial vehicle inspection, and particularly discloses an unmanned aerial vehicle inspection system for an oil and gas station. The system comprises an oil and gas station data extraction module, an unmanned aerial vehicle path analysis module, an oil and gas station environment detection module, an unmanned aerial vehicle path confirmation module, an oil and gas station area detection module, an oil and gas station area analysis module, an oil and gas station area confirmation module and an oil and gas station abnormity feedback terminal. According to the inspection data of each historical inspection of the oil and gas station and the safety level of each inspection area, the inspection information of each inspection of the unmanned aerial vehicle in the oil and gas station is analyzed, so that the rationality of the inspection path planning of the unmanned aerial vehicle is guaranteed; the abnormal indexes of the inspection areas in the oil and gas station are analyzed, the timeliness of fault early warning of the oil and gas station is guaranteed, prediction and analysis of the fault trend of the oil and gas station equipment are further guaranteed, and the timeliness of finding potential problems of the oil and gas station equipment is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of unmanned aerial vehicle inspection, and relates to an unmanned aerial vehicle inspection system for an oil and gas station. Background Art

[0002] The oil and gas station drone inspection system is an intelligent system that uses drone technology to perform safety inspections, equipment inspections, and other operations on oil and gas stations. It can replace manual inspections of some complex, dangerous, or difficult-to-reach areas, effectively improving inspection efficiency and accuracy.

[0003] For example, the Chinese invention patent with publication number CN110673628A discloses a composite wing UAV oil and gas pipeline inspection method, which belongs to the field of oil and gas pipeline inspection technology. First, the ground station sets the initial parameters and plans the route, and simultaneously mounts a hyperspectral camera, a visible light camera and an airborne image processor on the composite wing UAV platform to conduct a full-course autonomous inspection of the oil and gas pipeline. Then the composite wing UAV flies along the flight route, and the hyperspectral camera and the visible light camera simultaneously collect image information above and around the oil and gas pipeline, and perform real-time processing through the airborne image processor. The UAV transmits the images collected by the hyperspectral camera and the visible light camera to the ground station in real time through the data link, and transmits the abnormal situation information detected by the airborne image processor to the ground station. When the ground station finds an abnormal situation, it immediately alarms the ground personnel, reminds the ground personnel to pay attention, and takes corresponding measures in time. The present invention improves the efficiency, accuracy and real-time performance of the entire inspection process.

[0004] For example, the Chinese invention patent with publication number CN114967759B discloses a drone inspection system for defect identification of oil and gas field equipment. Compared with the prior art, the drone inspection system of the present invention also includes a drone flying to the corresponding area of ​​the oil and gas plant, a camera device arranged on the drone to obtain images of the pipeline equipment in the corresponding area of ​​the oil and gas plant, a management module for unified reception and management of the drone, and an image recognition unit for receiving the image information obtained by the drone and further analyzing and processing the conditions of each pipeline equipment. The present invention automatically manages the drone so that the drone can continuously detect the pipeline equipment of the oil and gas field, thereby timely identifying the defects of the pipeline equipment.

[0005] The above existing technologies have the following deficiencies: 1. The current drone inspection of oil and gas stations mainly collects and analyzes image information above the oil and gas pipelines and the surrounding environment. It does not consider the planning of drone inspection routes based on the historical inspection data and safety level information of the oil and gas stations. It cannot guarantee the rationality of drone inspection route planning, which increases the probability of repeated inspections and missed inspections, thereby increasing the flight distance of the drone. At the same time, it cannot guarantee the rationality of the inspection frequency allocation during drone inspections, which leads to a waste of drone inspection resources.

[0006] 2. The current drone inspection is mainly for defect identification of oil and gas station equipment. It only conducts oil and gas station fault identification and analysis from a single dimension, which cannot guarantee the timeliness of oil and gas station fault warning, and thus cannot guarantee the predictive analysis of oil and gas station equipment failure trends, and cannot timely discover potential problems of oil and gas station equipment, thus failing to guarantee the comprehensiveness of oil and gas station inspection analysis, and at the same time leads to increased safety risks of oil and gas stations. Summary of the invention

[0007] In view of this, in order to solve the problems raised in the above background technology, an oil and gas station drone inspection system is proposed.

[0008] The purpose of the present invention can be achieved through the following technical solutions: The present invention provides an oil and gas station drone inspection system, including: an oil and gas station data extraction module, which is used to extract the inspection data of each historical inspection of the oil and gas station and the safety level of each inspection area.

[0009] The drone path analysis module is used to analyze the inspection information of each drone inspection in the oil and gas station based on the inspection data of each historical inspection of the oil and gas station and the safety level of each inspection area.

[0010] The oil and gas station environmental detection module is used to extract the inspection time of each inspection of the drone in the oil and gas station from the inspection information of each inspection of the drone in the oil and gas station, and then detect the environmental information of each inspection area during each inspection of the drone in the oil and gas station, including wind speed and wind direction.

[0011] The drone path confirmation module is used to confirm the actual inspection path of the drone during each inspection in the oil and gas station based on the environmental information of each inspection area during each inspection of the drone in the oil and gas station.

[0012] The oil and gas station area detection module is used to detect the inspection information of each inspection area in the oil and gas station according to the actual inspection path of the UAV during each inspection in the oil and gas station, including the appearance image of each oil and gas equipment, the temperature of each oil and gas equipment at each inspection time point, and the inspection image at each inspection time point.

[0013] The oil and gas station area analysis module is used to analyze the abnormal index of each inspection area in the oil and gas station based on the inspection information of each inspection area in the oil and gas station.

[0014] The oil and gas station area confirmation module is used to confirm each abnormal inspection area in the oil and gas station according to the abnormal index of each inspection area in the oil and gas station.

[0015] The oil and gas station abnormal feedback terminal is used to provide corresponding feedback based on the abnormal inspection areas in the oil and gas station.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention analyzes the inspection information of each drone inspection in the oil and gas station based on the inspection data of each historical inspection of the oil and gas station and the safety level of each inspection area, thereby avoiding the current deficiency of not considering the historical inspection data and safety level information of the oil and gas station for drone inspection path planning, ensuring the rationality of drone inspection path planning, and thus reducing the probability of repeated inspections and missed inspections, thereby reducing the flight distance of the drone, while ensuring the rationality of the inspection frequency allocation during drone inspections and reducing the waste of drone inspection resources.

[0017] (2) The present invention analyzes the abnormal index of each inspection area in the oil and gas station based on the inspection information of each inspection area in the oil and gas station, breaking the current deficiency of only conducting fault identification and analysis of the oil and gas station from a single dimension, and conducting a more comprehensive inspection and analysis of the oil and gas station from dimensions such as appearance images, temperature and open flame images, thereby ensuring the timeliness of oil and gas station fault warnings, and further ensuring the predictive analysis of oil and gas station equipment failure trends, thereby improving the timeliness of discovering potential problems of oil and gas station equipment and reducing the safety risks of oil and gas stations.

[0018] (3) The present invention improves the inspection efficiency of drone inspections by confirming the actual inspection path of the drone at each inspection in the oil and gas station based on the environmental information of each inspection area during each inspection in the oil and gas station, thereby improving the inspection quality of the drone inspection, thereby enhancing the safety of the oil and gas station equipment and optimizing the allocation of drone inspection resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0020] Figure 1 It is a schematic diagram of the connection of each module of the system of the present invention.

[0021] Figure 2 It is a connection schematic diagram of the steps for confirming the actual inspection path of each inspection of the UAV of the present invention in the oil and gas station.

[0022] Figure 3 It is a schematic diagram of the connection steps of the statistical analysis of the abnormal open fire index in each inspection area of ​​the oil and gas station of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] See also Figure 1 As shown, the present invention provides an oil and gas station UAV inspection system, which includes: an oil and gas station data extraction module, a UAV path analysis module, an oil and gas station environment detection module, a UAV path confirmation module, an oil and gas station area detection module, an oil and gas station area analysis module, an oil and gas station area confirmation module and an oil and gas station abnormal feedback terminal.

[0025] In the above, the UAV path analysis module is respectively connected to the oil and gas station data extraction module and the oil and gas station environment detection module, the UAV path confirmation module is respectively connected to the oil and gas station environment detection module and the oil and gas station area detection module, the oil and gas station area analysis module is respectively connected to the oil and gas station area detection module and the oil and gas station area confirmation module, and the oil and gas station area confirmation module is also respectively connected to the oil and gas station area analysis module and the oil and gas station abnormal feedback terminal.

[0026] The oil and gas station data extraction module is used to extract the inspection data of each historical inspection of the oil and gas station and the safety level of each inspection area.

[0027] It should be added that the inspection data of each historical inspection of the oil and gas station and the safety level of each inspection area are extracted from the oil and gas station inspection record database.

[0028] The drone path analysis module is used to analyze the inspection information of each drone inspection in the oil and gas station based on the inspection data of each historical inspection of the oil and gas station and the safety level of each inspection area.

[0029] Exemplarily, the analysis of the inspection information of each inspection of the UAV in the oil and gas station includes: extracting the number of faults and the fault level of each fault in each inspection area of ​​the oil and gas station from the inspection data of each historical inspection of the oil and gas station, and then calculating the fault impact index φ of each inspection area in the oil and gas station i , i is the inspection area number, i=1,2,......,m.

[0030] It should be added that the statistical process of calculating the fault impact index of each inspection area in the oil and gas station is as follows: the fault level of each inspection area in the oil and gas station in each fault is matched and compared with the fault level corresponding to each fault impact coefficient to obtain the fault risk coefficient of each inspection area in the oil and gas station in each fault.

[0031] The maximum value is extracted from the failure risk coefficient of each inspection area in the oil and gas station in each failure, which is taken as the maximum failure risk coefficient of each inspection area in the oil and gas station, denoted as ε i .

[0032] The average failure risk coefficient of each inspection area in the oil and gas station is calculated for each failure, and the average failure risk coefficient of each inspection area in the oil and gas station is obtained.

[0033] The number of failures in each inspection area of ​​the oil and gas station is recorded as D i .

[0034] Statistical fault impact index φ of each inspection area in the oil and gas station i , ε′ and D′ are the failure risk coefficient and failure number of the set reference respectively.

[0035] It should be added that ε′ is the failure risk coefficient with the highest number of occurrences extracted from the failure risk coefficients of each inspection area in the oil and gas station as the failure risk coefficient for setting reference, and D′ is obtained by calculating the average number of failures in each inspection area in the oil and gas station, and using the calculation result as the number of failures for setting reference.

[0036] The safety level of each inspection area in the oil and gas station is matched and compared with the safety level corresponding to each safety impact index, and the safety impact coefficient of each inspection area in the oil and gas station is obtained, which is recorded as φ i ′.

[0037] Statistical analysis of the risk factors of each inspection area in oil and gas stations

[0038] The current inspection frequency of each inspection area in the oil and gas station is extracted from the inspection data of each historical inspection of the oil and gas station, which is recorded as γ i .

[0039] The average risk factor of each inspection area in the oil and gas station is calculated, and the average risk factor of the oil and gas station is obtained, which is recorded as

[0040] Statistics on the inspection frequency of each inspection area in the oil and gas stationγ i ′, To round up.

[0041] The set starting inspection time point of the oil and gas station is extracted from the inspection data of each historical inspection of the oil and gas station, and then the inspection time of each inspection of the drone in the oil and gas station is obtained according to the inspection frequency of each inspection area in the oil and gas station.

[0042] According to the inspection frequency of each inspection area in the oil and gas station, the inspection areas of each inspection of the UAV in the oil and gas station are obtained.

[0043] According to the inspection areas of each inspection of the UAV in the oil and gas station, the planned inspection paths of the UAV during each inspection are planned, and the planned inspection paths of the UAV during each inspection are sorted from large to small according to the path length, so as to extract the planned inspection path with the last one in the sorting as the inspection path of the UAV for each inspection in the oil and gas station.

[0044] The inspection time and inspection path of each inspection of the UAV in the oil and gas station are used as the inspection information of each inspection of the UAV in the oil and gas station.

[0045] The embodiment of the present invention analyzes the inspection information of each drone inspection in the oil and gas station based on the inspection data of each historical inspection of the oil and gas station and the safety level of each inspection area, thereby avoiding the shortcoming of the current drone inspection path planning that does not consider the historical inspection data and safety level information of the oil and gas station, ensuring the rationality of the drone inspection path planning, and further reducing the probability of repeated inspections and missed inspections, thereby reducing the flight distance of the drone, while ensuring the rationality of the inspection frequency allocation during the drone inspection and reducing the waste of drone inspection resources.

[0046] The oil and gas station environmental detection module is used to extract the inspection time of each inspection of the drone in the oil and gas station from the inspection information of each inspection of the drone in the oil and gas station, and then detect the environmental information of each inspection area during each inspection of the drone in the oil and gas station, including wind speed and wind direction.

[0047] It should be added that the wind speed and direction of each inspection area during each inspection of the oil and gas station by the drone are obtained through detection by an ultrasonic anemometer. Its working principle is as follows: the wind speed and direction are determined by measuring the propagation time difference of the ultrasonic pulse in the air. The instrument emits two fixed-frequency ultrasonic waves in the wind direction. Due to the influence of wind speed, the two ultrasonic waves will produce a time difference. According to the time difference, the wind speed value is calculated. At the same time, based on the Doppler effect, the time shift of the echo of particles blown by the wind within the short flight range is counted, and the echo signal containing different frequency components is received by the instrument. The time domain signal is converted into a frequency domain signal through spectrum analysis methods such as fast Fourier transform (FFT). The frequency distribution can be clearly seen in the frequency domain, and then according to the Doppler frequency shift formula Among them, Δf is the frequency shift, v is the speed of the particle in the wind direction, f0 is the original frequency, and c is the propagation speed of the ultrasonic wave in the air. The instrument determines the wind direction by emitting two fixed-frequency ultrasonic waves. Generally speaking, the emission directions of the two ultrasonic waves are different. For example, one has an angle of θ1′ with the preset reference direction (such as the front of the instrument), and the other has an angle of θ2′. After calculating the speeds v1″ and v′2′ of the particle relative to these two different directions, the wind direction is determined according to the trigonometric function relationship. Assuming that the location of the instrument is the origin of the coordinate system, a plane rectangular coordinate system is established. For the first ultrasonic direction, the components of the particle speed on the x-axis (horizontal direction) and the y-axis (vertical direction) are v1″ and v2′, respectively. x =v1″*cosθ1′ and v1″ y =v1″*sinθ1′, for the second ultrasonic direction, the particle velocity component is v′2′ x =v′2′*cosθ2′ and v′2′ y =v′2′*sinθ2′.

[0048] Determination of wind direction angle: First calculate the horizontal velocity component difference Δv′ x ′=v′2′ x -v1″ x and the vertical velocity component difference Δv′ y ′=v′2′ y -v1″ y , calculate the wind direction angle according to the inverse tangent function The obtained θ value is the angle between the wind direction and the preset reference direction, thereby determining the wind direction.

[0049] The drone path confirmation module is used to confirm the actual inspection path of the drone during each inspection in the oil and gas station based on the environmental information of each inspection area during each inspection by the drone in the oil and gas station.

[0050] See also Figure 2 As shown, for example, the method of confirming the actual inspection path of each inspection of the drone in the oil and gas station includes: A1, according to the inspection path of each inspection of the drone and the wind speed of each inspection area, calculating the wind interference coefficient F of each inspection area during each inspection of the drone ij , j is the inspection sequence number, j=1,2,......,n.

[0051] Furthermore, the statistical wind interference coefficient of each inspection area during each inspection of the drone includes: A1-1, recording the wind speed of each inspection area during each inspection of the drone as v ij .

[0052] A1-2. Statistical analysis of wind speed influence coefficient β in each inspection area during each inspection by the drone ij , v′ is the wind speed threshold for setting reference.

[0053] It should be added that v′ is obtained by extracting the maximum wind speed of the drone in each inspection area during each inspection as the wind speed threshold for setting the reference.

[0054] A1-3. Extract the flight direction of the drone in each inspection area from the inspection path of each inspection, and then use the angle between it and the wind direction as the wind direction interference angle, denoted as θ ij , so as to calculate the wind direction influence coefficient α of each inspection area during each inspection by the drone ij .

[0055] Furthermore, the statistical wind direction influence coefficient of each inspection area during each inspection of the drone includes: A1-3-1, the flight speed of the drone in each inspection area during each inspection is recorded as v i ' j .

[0056] A1-3-2. Calculate the wind direction influence coefficient α in each inspection area during each inspection by the drone ij ,

[0057]

[0058] In a specific embodiment, during the first inspection, the wind speed in area 1 is v 11 =3m / s, the flying speed of the drone is v1′1=10m / s, and the wind speed in area 2 is v 12 =5m / s, the flying speed of the drone is v1′2=8m / s, and the wind speed in area 3 is v 13 =2m / s, the flying speed of the UAV is v1′3=12m / s.

[0059] During the first inspection, the drone flew from east to west in area 1. The wind direction in the area was due south at that time, and the wind interference angle was θ 11 =90°, in area 2, the drone flies from south to north, the wind direction is northwest, and the wind interference angle is θ 12 =45°, in area 3, the drone flies from west to east, the wind direction is southwest, and the wind interference angle is θ 13 =135°.

[0060] First inspection: Area 1: Because v 11 <v′, then Region 2: Because v 12 >v′, then β 12 =1, Region 3: Because v 13 <v′, then

[0061] Calculation of wind direction influence coefficient: First inspection: Area 1: Region 2: Region 3:

[0062]

[0063] Wind interference coefficient calculation: First inspection: Area 1: F 11 =α 11 *β 11 =1*0.75=0.75, Area 2: F 12 =α 12 *β 12 =0.5*1=0.5, Area 3: F 13 =α 13 *β 13 =1.33*0.5=0.665.

[0064] A1-4. Count the wind interference coefficient F in each inspection area during each inspection by the drone ij , F ij =α ij *β ij .

[0065] A2. Compare the wind interference coefficient of each inspection area of ​​the drone with the set permissible wind interference coefficient.

[0066] A3. If the wind interference coefficient of a certain inspection area during a drone inspection is greater than the set permissible wind interference coefficient, the inspection area during the drone inspection will be recorded as a wind interference inspection area.

[0067] A4. Count the number of wind-interfered inspection areas and the number of inspection areas during each inspection by the drone, and use the ratio of the number of wind-interfered inspection areas to the number of inspection areas during each inspection by the drone as the wind interference ratio during each inspection by the drone.

[0068] A5. The wind interference ratio of each drone inspection is introduced into the drone inspection path analysis model to obtain the actual inspection path of each drone inspection in the oil and gas station.

[0069] It should be added that the analysis process of the UAV inspection path analysis model is as follows: the wind interference ratio of each UAV inspection is compared with the set wind interference ratio. If the wind interference ratio of the UAV during a certain inspection is less than or equal to the set wind interference ratio, the inspection path of the UAV for that inspection will be used as the actual inspection path of the UAV for that inspection.

[0070] If the wind interference ratio of the UAV during a certain inspection is greater than the set wind interference ratio, the planned inspection paths of the UAV during this inspection are extracted, and then the wind interference ratios of the planned inspection paths of the UAV during this inspection are obtained by similar analysis method according to the wind interference ratio of the UAV during this inspection, and the minimum value is screened out, and the planned inspection path to which the minimum value belongs is used as the actual inspection path of the UAV for this inspection, thereby obtaining the actual inspection paths of the UAV for each inspection in the oil and gas station.

[0071] The embodiment of the present invention improves the inspection efficiency of the drone inspection and then improves the inspection quality of the drone inspection by confirming the actual inspection path of the drone at each inspection in the oil and gas station based on the environmental information of each inspection area during each inspection in the oil and gas station, thereby enhancing the safety of the oil and gas station equipment and optimizing the allocation of drone inspection resources.

[0072] The oil and gas station area detection module is used to detect the inspection information of each inspection area in the oil and gas station according to the actual inspection path of the drone during each inspection in the oil and gas station, including the appearance image of each oil and gas equipment, the temperature of each oil and gas equipment at each inspection time point, and the inspection image at each inspection time point.

[0073] It should be added that the appearance images of each oil and gas equipment in each inspection area of ​​the oil and gas station and the inspection images at each inspection time point are all captured by the camera carried by the drone.

[0074] It should be added that the temperature of each oil and gas equipment in each inspection area of ​​the oil and gas station at each detection time point is obtained by detecting the infrared thermal imager carried by the drone. Its working principle is: the infrared thermal imager uses an infrared detector and an optical imaging objective to receive the infrared radiation energy distribution pattern of the target being measured, and reflects it on the photosensitive element of the infrared detector, thereby obtaining an infrared thermal image. This thermal image corresponds to the temperature distribution on the surface of the object. By analyzing the thermal image, the temperature distribution on the surface of the object is determined. For example: when a drone equipped with an infrared thermal imager flies over the tank area of ​​the oil and gas station, the thermal imager can capture the infrared radiation energy of different parts of the tank surface. Since the temperature of different parts of the tank may be different (for example, the temperature of the part close to the heating device may be higher, while the temperature of other parts is relatively low), the infrared thermal imager will display these temperature differences on the thermal image in different colors or grayscale levels, and then obtain the temperature of each oil and gas equipment in each inspection area of ​​the oil and gas station at each detection time point.

[0075] The oil and gas station area analysis module is used to analyze the abnormal index of each inspection area in the oil and gas station according to the inspection information of each inspection area in the oil and gas station.

[0076] Exemplarily, the analysis of the abnormality index of each inspection area in the oil and gas station includes: B1, according to the appearance image of each oil and gas equipment in each inspection area in the oil and gas station, calculating the appearance abnormality index η of each inspection area in the oil and gas station i .

[0077] Furthermore, the statistical appearance abnormality index of each inspection area in the oil and gas station includes: B1-1, extracting the number of damaged parts of each oil and gas equipment in each inspection area in the oil and gas station and the damaged area of ​​each damaged part from the appearance image of each oil and gas equipment in each inspection area in the oil and gas station.

[0078] B1-2. Select the maximum damaged area of ​​each oil and gas equipment in each inspection area from the damaged areas of each oil and gas equipment in each inspection area, and record it as S iq , q is the oil and gas equipment number, q=1,2,......,p.

[0079] B1-3. Calculate the average damaged area of ​​each damaged part of each oil and gas equipment in each inspection area to obtain the average damaged area of ​​each oil and gas equipment in each inspection area, recorded as

[0080] B1-4. The number of damaged parts of each oil and gas equipment in each inspection area of ​​the oil and gas station is recorded as D iq .

[0081] B1-5. Calculate the appearance abnormality index η of each inspection area in the oil and gas station i , e is a natural constant, S′ and D′ are the damaged area and number of damaged parts respectively.

[0082] It should be added that the reference damaged area and number of damaged items are set as follows: extract the appearance damage data of each oil and gas equipment in the oil and gas station over the past period of time (such as 1-3 years) from the oil and gas station inspection record database, including the damaged area, the number of damaged items, and the corresponding maintenance records, equipment operating conditions and other information, perform statistical analysis on these data, and obtain the common damage area range and the distribution of the number of damaged items for each oil and gas equipment, and set the reference damaged area and number of damaged items based on this. Example: Through statistics on the inspection data of the past two years, it is found that the damage area of ​​oil and gas equipment in the oil and gas station is mainly concentrated between 0.2 and 0.5 square meters, and the average number of damaged items is 3 to 5. Taking into account factors such as the importance of the equipment and maintenance costs, the reference damaged area of ​​the oil and gas equipment is set to 0.3 square meters, and the reference number of damaged items is set to 4.

[0083] B2. According to the temperature of each oil and gas equipment in each inspection area of ​​the oil and gas station at each detection time point, the temperature anomaly index η of each inspection area in the oil and gas station is calculated i ′.

[0084] Furthermore, the statistical temperature anomaly index of each inspection area in the oil and gas station includes: B2-1, using the detection time point as the horizontal coordinate and the temperature as the vertical coordinate to construct a temperature change curve of each oil and gas equipment in each inspection area of ​​the oil and gas station.

[0085] B2-2. Each detection time point of each oil and gas equipment in each inspection area of ​​the oil and gas station and its next adjacent detection time point form a detection time group to obtain each detection time group of each oil and gas equipment in each inspection area of ​​the oil and gas station.

[0086] B2-3. Extract the slope of each detection time group of each oil and gas equipment in each inspection area of ​​the oil and gas station from the temperature change curve, and use it as the temperature change rate of each oil and gas equipment in each inspection area of ​​the oil and gas station in each detection time group, and extract the maximum value from it as the temperature change rate of each oil and gas equipment in each inspection area of ​​the oil and gas station.

[0087] B2-4. Extract the maximum temperature of each oil and gas equipment in each inspection area of ​​the oil and gas station from the temperature of each oil and gas equipment in each inspection area of ​​the oil and gas station at each detection time point.

[0088] B2-5. The maximum temperature of the oil and gas equipment in the inspection area of ​​the oil and gas station is greater than the set oil and gas equipment temperature threshold as condition one, and the temperature change rate of the oil and gas equipment in the inspection area of ​​the oil and gas station is greater than the set reference temperature change rate as condition two.

[0089] B2-6. When both condition 1 and condition 2 are not met, 0 is used as the temperature anomaly index of the inspection area in the oil and gas station. Otherwise, 1 is used as the temperature anomaly index of the inspection area in the oil and gas station. Then, the temperature anomaly index of each inspection area in the oil and gas station is obtained, which is recorded as η. i ′.

[0090] B3. According to the inspection images of each inspection area in the oil and gas station at each detection time point, the open fire abnormality index η of each inspection area in the oil and gas station is calculated i ″.

[0091] See also Figure 3 As shown, further, the statistical open flame abnormality index of each inspection area in the oil and gas station includes: B3-1, judging the presence of open flame based on the inspection images of each inspection area in the oil and gas station at each detection time point.

[0092] It should be added that the method for judging the presence of open flames is obtained through the color threshold method, and its working principle is: open flames usually have a specific color range, mainly concentrated in warm tones such as red, orange and yellow. By setting the threshold range of these colors in different color spaces (such as RGB, HSV, etc.), areas that may contain open flames are screened out. Specific examples: in the RGB color space, the possible range of the red area is R (150-255), G (0-50), B (0-50), in the HSV color space, H (0-30 or 330-360), S (50-255), V (100-255), etc., each pixel of the inspection image is traversed to determine whether its color value is within the set threshold range. If the number of pixels that meet the threshold condition in a certain area exceeds the threshold (such as 5%), it is determined that there is an open flame in the area.

[0093] B3-2. If an open fire appears in the inspection image of a certain inspection area in the oil and gas station at a certain detection time point, the open fire abnormality index of the inspection area in the oil and gas station is recorded as 1. Otherwise, the open fire abnormality index of the inspection area in the oil and gas station is recorded as 0. Then, the open fire abnormality index of each inspection area in the oil and gas station is obtained, which is recorded as η i ″.

[0094] B4. Calculate the abnormal index λ of each inspection area in the oil and gas station i ,λ i =η i *w1+η i ′*w2+η i ″*w3, w1, w2 and w3 are the weights of the set appearance abnormality index, temperature abnormality index and open flame abnormality index respectively, w1+w2+w3=1, w3>w2>w1.

[0095] It should be added that in the oil and gas station environment, open flames are the most direct and serious safety threat. Once open flames appear, it is very likely to cause explosions and large-scale fires, causing devastating consequences to personnel life safety, oil and gas station facilities and the surrounding environment. For example, if a small spark comes into contact with the combustible mixture formed by oil and gas leakage, it may instantly cause violent combustion and explosion. This catastrophic consequence is difficult to achieve in a short period of time due to abnormal appearance and temperature, so it has the highest weight. Abnormal temperature is often an important early signal of equipment failure or potential safety hazards. For example, excessively high local temperature in an oil pipeline may indicate increased friction and blockage inside the pipeline, or chemical reactions after oil and gas leakage. If not handled in time, as the temperature continues to rise abnormally, it will increase the oil and gas. The risk of spontaneous combustion or other safety accidents. Although temperature abnormality itself may not immediately cause serious accidents such as explosions like open flames, it is a key intermediate link, so its weight is second only to open flames. Appearance abnormalities usually include damage to the surface of equipment. These problems generally do not directly lead to catastrophic accidents, but may affect the service life, performance and operating efficiency of the equipment. For example, slight corrosion on the surface of the oil tank may gradually weaken the strength of the tank, but this process is relatively slow, and after the appearance abnormality is discovered, there is still time to evaluate, repair and replace it. Therefore, its weight is the lowest. Therefore, set w3>w2>w1. For the convenience of analysis, w1 can be specifically taken as 0.2, w2 can be specifically taken as 0.3, and w3 can be specifically taken as 0.5.

[0096] The embodiment of the present invention analyzes the abnormal index of each inspection area in the oil and gas station according to the inspection information of each inspection area in the oil and gas station, breaking the current deficiency of only conducting fault identification and analysis of the oil and gas station from a single dimension, and conducting a more comprehensive inspection and analysis of the oil and gas station from dimensions such as appearance image, temperature and open flame image, and ensuring the timeliness of oil and gas station fault warning, and further ensuring the predictive analysis of oil and gas station equipment failure trends, thereby improving the timeliness of discovering potential problems of oil and gas station equipment and reducing the safety risks of oil and gas stations.

[0097] The oil and gas station area confirmation module is used to confirm each abnormal inspection area in the oil and gas station according to the abnormal index of each inspection area in the oil and gas station.

[0098] Exemplarily, the confirming each abnormal inspection area in the oil and gas station includes: comparing an abnormality index of each inspection area in the oil and gas station with a set reference abnormality index.

[0099] If the abnormal index of a certain inspection area in the oil and gas station is greater than the set reference abnormal index, the inspection area in the oil and gas station is recorded as an abnormal inspection area, and then the abnormal inspection areas in the oil and gas station are obtained.

[0100] The oil and gas station abnormality feedback terminal is used to provide corresponding feedback according to each abnormal inspection area in the oil and gas station.

[0101] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. Oil and gas station drone inspection system, characterized by: The system includes: The oil and gas station data extraction module is used to extract the inspection data of each historical inspection of the oil and gas station and the safety level of each inspection area; The drone path analysis module is used to analyze the inspection information of each drone inspection in the oil and gas station based on the inspection data of each historical inspection of the oil and gas station and the safety level of each inspection area; The oil and gas station environment detection module is used to extract the inspection time of each inspection of the UAV in the oil and gas station from the inspection information of each inspection of the UAV in the oil and gas station, and then detect the environmental information of each inspection area during each inspection of the UAV in the oil and gas station, including wind speed and wind direction; The drone path confirmation module is used to confirm the actual inspection path of the drone at each inspection in the oil and gas station according to the environmental information of each inspection area during each inspection of the drone in the oil and gas station; The oil and gas station area detection module is used to detect the inspection information of each inspection area in the oil and gas station according to the actual inspection path of the drone during each inspection in the oil and gas station, including the appearance image of each oil and gas equipment, the temperature of each oil and gas equipment at each inspection time point, and the inspection image at each inspection time point; The oil and gas station area analysis module is used to analyze the abnormal index of each inspection area in the oil and gas station based on the inspection information of each inspection area in the oil and gas station; The oil and gas station area confirmation module is used to confirm each abnormal inspection area in the oil and gas station according to the abnormal index of each inspection area in the oil and gas station; The oil and gas station abnormal feedback terminal is used to provide corresponding feedback based on the abnormal inspection areas in the oil and gas station.

2. The oil and gas station drone inspection system according to claim 1 is characterized by: The analysis of the inspection information of each inspection of the drone in the oil and gas station includes: The number of faults and the fault level of each fault in each inspection area of ​​the oil and gas station are extracted from the inspection data of each historical inspection of the oil and gas station, and then the fault impact index φ of each inspection area of ​​the oil and gas station is calculated. i , i is the inspection area number, i=1,2,......,m; The safety level of each inspection area in the oil and gas station is matched and compared with the safety level corresponding to each safety impact index, and the safety impact coefficient of each inspection area in the oil and gas station is obtained, which is recorded as φ i ′; Statistical analysis of the risk factors of each inspection area in oil and gas stations The current inspection frequency of each inspection area in the oil and gas station is extracted from the inspection data of each historical inspection of the oil and gas station, which is recorded as γ i ; The average risk factor of each inspection area in the oil and gas station is calculated, and the average risk factor of the oil and gas station is obtained, which is recorded as Statistics on the inspection frequency of each inspection area in the oil and gas stationγ i ′, To round up; Extract the set starting inspection time point of the oil and gas station from the inspection data of each historical inspection of the oil and gas station, and then obtain the inspection time of each inspection of the drone in the oil and gas station according to the inspection frequency of each inspection area in the oil and gas station; According to the inspection frequency of each inspection area in the oil and gas station, the inspection areas of each inspection of the drone in the oil and gas station are obtained; According to the inspection areas of each inspection of the drone in the oil and gas station, the planned inspection paths of the drone during each inspection are planned, and the planned inspection paths of the drone during each inspection are sorted from large to small according to the path length, so as to extract the planned inspection path with the last position in the sorting as the inspection path of each inspection of the drone in the oil and gas station; The inspection time and inspection path of each inspection of the UAV in the oil and gas station are used as the inspection information of each inspection of the UAV in the oil and gas station.

3. The oil and gas station drone inspection system according to claim 2 is characterized by: The confirmation of the actual inspection path of each inspection of the drone in the oil and gas station includes: A1. According to the inspection path of each drone inspection and the wind speed in each inspection area, the wind interference coefficient F of each drone inspection in each inspection area is calculated. ij , j is the inspection sequence number, j = 1, 2, ..., n; A2. Compare the wind interference coefficient of each inspection area of ​​the drone with the set permissible wind interference coefficient; A3. If the wind interference coefficient of a certain inspection area during a drone inspection is greater than the set permissible wind interference coefficient, the inspection area during the drone inspection will be recorded as a wind interference inspection area; A4. Count the number of wind-interfered inspection areas and the number of inspection areas during each inspection by the drone, and use the ratio of the number of wind-interfered inspection areas to the number of inspection areas during each inspection by the drone as the wind interference ratio during each inspection by the drone; A5. The wind interference ratio of each drone inspection is introduced into the drone inspection path analysis model to obtain the actual inspection path of each drone inspection in the oil and gas station.

4. The oil and gas station drone inspection system according to claim 3 is characterized by: The statistical wind interference coefficient of each inspection area during each inspection of the drone includes: The wind speed of the drone in each inspection area during each inspection is recorded as v ij ; Statistics of wind speed influence coefficient β in each inspection area during each inspection by drone ij , v′ is the wind speed threshold for setting reference; The flight direction of the drone in each inspection area is extracted from the inspection path of each inspection by the drone, and then the angle between it and the wind direction is used as the wind direction interference angle, recorded as θ ij , so as to calculate the wind direction influence coefficient α of each inspection area during each inspection by the drone ij ; Statistics of wind interference coefficient F in each inspection area during each inspection by drone ij , F ij =α ij *β ij .

5. The oil and gas station drone inspection system according to claim 4 is characterized by: The statistical wind direction influence coefficient of each inspection area during each inspection of the drone includes: The flying speed of the UAV in each inspection area during each inspection is recorded as v i ' j ; Statistics of wind direction influence coefficient α in each inspection area during each inspection by drone ij , 6. The oil and gas station drone inspection system according to claim 1, characterized in that: The analysis of abnormal indexes of each inspection area in the oil and gas station includes: B1. According to the appearance images of each oil and gas equipment in each inspection area of ​​the oil and gas station, the appearance abnormality index η of each inspection area in the oil and gas station is calculated. i ; B2. According to the temperature of each oil and gas equipment in each inspection area of ​​the oil and gas station at each detection time point, the temperature anomaly index η of each inspection area in the oil and gas station is calculated i ′; B3. According to the inspection images of each inspection area in the oil and gas station at each detection time point, the open fire abnormality index η of each inspection area in the oil and gas station is calculated i ″; B4. Calculate the abnormal index λ of each inspection area in the oil and gas station i ,λ i =η i *w1+η i ′*w2+η i ″*w3, w1, w2 and w3 are the weights of the set appearance abnormality index, temperature abnormality index and open flame abnormality index respectively, w1+w2+w3=1, w3>w2>w1.

7. The oil and gas station drone inspection system according to claim 6, characterized in that: The statistical appearance abnormality index of each inspection area in the oil and gas station includes: Extracting the number of damaged parts of each oil and gas equipment in each inspection area of ​​the oil and gas station and the damaged area of ​​each damaged part from the appearance image of each oil and gas equipment in each inspection area of ​​the oil and gas station; The maximum damaged area of ​​each oil and gas equipment in each inspection area is selected from the damaged areas of each oil and gas equipment in each inspection area, and recorded as S iq , q is the oil and gas equipment number, q=1,2,......,p; The average damaged area of ​​each damaged part of each oil and gas equipment in each inspection area is calculated, and the average damaged area of ​​each oil and gas equipment in each inspection area is obtained, which is recorded as The number of damaged parts of each oil and gas equipment in each inspection area of ​​the oil and gas station is recorded as D iq ; Statistical analysis of the appearance anomaly index η of each inspection area in the oil and gas station i , e is a natural constant, S′ and D′ are the damaged area and number of damaged parts respectively.

8. The oil and gas station drone inspection system according to claim 6, characterized in that: The statistical temperature anomaly index of each inspection area in the oil and gas station includes: With the detection time point as the horizontal coordinate and the temperature as the vertical coordinate, a temperature change curve of each oil and gas equipment in each inspection area of ​​the oil and gas station is constructed; Each detection time point of each oil and gas equipment in each inspection area of ​​the oil and gas station and its next adjacent detection time point constitute a detection time group, so as to obtain each detection time group of each oil and gas equipment in each inspection area of ​​the oil and gas station; Extracting the slope of each detection time group of each oil and gas equipment in each inspection area of ​​the oil and gas station from the temperature change curve as the temperature change rate of each oil and gas equipment in each inspection area of ​​the oil and gas station in each detection time group, and extracting the maximum value therefrom as the temperature change rate of each oil and gas equipment in each inspection area of ​​the oil and gas station; Extracting the maximum temperature of each oil and gas equipment in each inspection area of ​​the oil and gas station from the temperature of each oil and gas equipment at each inspection time point in the oil and gas station; The maximum temperature of the oil and gas equipment in the inspection area of ​​the oil and gas station is greater than the set oil and gas equipment temperature threshold as condition one, and the temperature change rate of the oil and gas equipment in the inspection area of ​​the oil and gas station is greater than the set reference temperature change rate as condition two; When both condition 1 and condition 2 are not met, 0 is taken as the temperature anomaly index of the inspection area in the oil and gas station. Otherwise, 1 is taken as the temperature anomaly index of the inspection area in the oil and gas station. Then, the temperature anomaly index of each inspection area in the oil and gas station is obtained, which is recorded as η. i ′,η i ′ takes the value of 1 or 0.

9. The oil and gas station drone inspection system according to claim 6, characterized in that: The statistical open fire abnormality index of each inspection area in the oil and gas station includes: According to the inspection images of each inspection area in the oil and gas station at each inspection time point, the presence of open flames is judged; If an open fire appears in the inspection image of a certain inspection area in the oil and gas station at a certain detection time point, the open fire abnormality index of the inspection area in the oil and gas station is recorded as 1, otherwise, the open fire abnormality index of the inspection area in the oil and gas station is recorded as 0, and then the open fire abnormality index of each inspection area in the oil and gas station is obtained, which is recorded as η i ″.

10. The oil and gas station drone inspection system according to claim 6, characterized in that: The confirmation of abnormal inspection areas in the oil and gas station includes: Compare the abnormal index of each inspection area in the oil and gas station with the abnormal index of the set reference; If the abnormal index of a certain inspection area in the oil and gas station is greater than the set reference abnormal index, the inspection area in the oil and gas station is recorded as an abnormal inspection area, and then the abnormal inspection areas in the oil and gas station are obtained.

Images