Automatic refueling control system based on artificial intelligence

Abstract

The invention belongs to the technical field of refueling control, and particularly discloses and provides an automatic refueling control system based on artificial intelligence, which comprises a target vehicle information detection module, a fuel tank cap position identification module, a fuel tank cap opening control module, an insertion posture confirmation module, a refueling confirmation execution module, a database and a refueling completion reset module. Through cooperative work of a plurality of modules, automation of the whole process from vehicle entering a gas station to refueling completion is achieved, efficient, safe and reliable operation of vehicle refueling is ensured, meanwhile, by confirming target insertion posture information of a refueling gun, the refueling gun is controlled to be inserted into a refueling port, and the refueling efficiency is improved. The problem of insufficient attention of preparation control before automatic refueling of the vehicle at present is effectively solved, the influence of the vehicle posture and the influence of the refueling posture are fully considered, fine control over the corresponding posture of the refueling oil gun is achieved, and the stability of the refueling process and the reliability of oil quantity control are guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of refueling control, and in particular, relates to an automatic refueling control system based on artificial intelligence. Background Art

[0002] With the continuous advancement of artificial intelligence, machine vision and automation technology, the traditional refueling method is facing major changes. Automated refueling has gradually become a popular refueling method. In order to improve the efficiency, safety and convenience of the refueling process, the refueling process needs to be controlled.

[0003] Prior art, such as a refueling monitoring system disclosed in a Chinese invention patent application with application number 201511003330.7, is mainly divided into two parts. The remote control includes the management layer and the control and detection layer. The operator can realize remote control through the local control panel of the PLC, and can understand the pipeline pressure, flow and other information in the refueling pipeline through the display on the control panel. The equipment layer shows the schematic diagram of the pump parallel system, including the layout of the power frequency pump, safety valve, refueling valve, reflux valve, and other devices, and also reflects the distribution position of the pressure and flow sensors. The entire equipment layer can be divided into three control systems, namely pump start and stop control, pipeline reflux control, loop part and pressure maintenance control. These three control systems cooperate with each other to complete the entire refueling process. Therefore, the operation is simple and easy to master, the overall structure of the device is simple, and the cost is low.

[0004] With regard to the above technical solutions, it is obvious that the current refueling control focuses on the control during the refueling process, and there are still the following deficiencies: 1. Insufficient attention is paid to the preparatory control before refueling, and the posture of the vehicle is not monitored, and the posture of the refueling gun is not controlled, which cannot guarantee the stability of the refueling process and the reliability of the oil quantity control.

[0005] 2. Lack of vehicle status check: Currently, there is no comprehensive detection of the vehicle's parking position, information about the oil in the tank, etc., which makes the subsequent automated refueling control less targeted, and thus cannot guarantee the standardization and flexibility of automated refueling. Summary of the invention

[0006] In view of this, in order to solve the problems raised in the above background technology, an automatic refueling control system based on artificial intelligence is proposed.

[0007] The purpose of the present invention can be achieved through the following technical solutions: The present invention provides an automatic refueling control system based on artificial intelligence, which includes: a target vehicle information detection module, which collects the parking image of the target vehicle when the target vehicle enters the gas station and stops at the designated position, and identifies the model of the target vehicle, and at the same time imports the environmental information in the gas station and the oil quality detection information in the corresponding oil storage tank at the designated position.

[0008] The fuel tank cap position recognition module is used to use the target detection algorithm to identify the fuel tank cap position of the target vehicle and send the fuel tank cap position to the fuel tank cap opening control module.

[0009] The fuel tank cap opening control module is used to start the robotic arm, and according to the position of the fuel tank cap, plan the motion path to move to the position of the fuel tank cap, and start the tool to unscrew the fuel tank cap.

[0010] The insertion posture confirmation module is used to automatically identify the position of the fuel tank opening, record the fuel tank opening information, and confirm the target insertion posture information of the fuel gun after the fuel tank cap is unscrewed.

[0011] The refueling confirmation execution module is used to control the refueling gun to be inserted into the fuel tank port based on the target insertion posture information of the refueling gun, and at the same time import the set refueling amount of the target vehicle, and confirm the appropriate refueling index. According to the appropriate refueling index, the refueling pump is started for refueling.

[0012] The database is used to store the rated storage oil level height and reference refueling insertion depth designed for each vehicle model, store the reference insertion depth of each tank port diameter, and store the initial grayscale histogram of the tank port edge corresponding to each vehicle model.

[0013] The refueling completion reset module is used to stop the refueling pump and pull out the refueling gun from the fuel tank port after refueling is completed. Then, the robotic arm uses a tool to tighten the fuel tank cap and reset the robotic arm and the refueling gun.

[0014] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention realizes the automation of the entire process from vehicle entering a gas station to completion of refueling through the collaborative work of multiple modules, ensuring efficient, safe and reliable operation of vehicle refueling, which not only improves the operational efficiency of the gas station, but also enhances the user experience and reduces human errors and safety hazards.

[0015] (2) The present invention controls the insertion of the fuel gun into the fuel tank port by confirming the target insertion posture information of the fuel gun, thereby effectively solving the current problem of insufficient attention to the preparatory control before automatic refueling of the vehicle. It fully considers the influence of the vehicle posture and the refueling posture, and realizes the refined control of the corresponding posture of the fuel gun, thereby ensuring the stability of the refueling process and the reliability of the oil quantity control.

[0016] (3) The present invention realizes multi-dimensional comprehensive detection by comprehensively confirming the parking characteristics of the target vehicle and considering the oil level height in the vehicle tank and the oil quality detection information in the corresponding oil storage cylinder at the designated position, thereby making up for the deficiency of the current lack of vehicle status inspection, facilitating the improvement of the targetedness of subsequent automatic refueling control, and at the same time ensuring the standardization and flexibility of automatic refueling.

[0017] (4) The present invention sets the fuel tank insertion depth limit factor by comprehensively considering the oil level limit ratio and the fuel tank height limit ratio, thereby effectively preventing overflow during refueling, thereby reducing environmental pollution and potential fire risks, improving the safety and adaptability of refueling posture settings, and optimizing the filling efficiency of automatic refueling, and reducing the risk of failure during the automatic refueling process. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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.

[0019] Figure 1 It is a schematic diagram of the connection of the system modules of the present invention.

[0020] Figure 2 It is a schematic diagram of the overall process of the present invention. DETAILED DESCRIPTION

[0021] 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.

[0022] See also Figure 1 and Figure 2 As shown, the present invention provides an automatic refueling control system based on artificial intelligence, which includes: a target vehicle information detection module, a fuel tank cap position recognition module, a fuel tank cap opening control module, an insertion posture confirmation module, a refueling confirmation execution module, a database and a refueling completion reset module.

[0023] In the above, the fuel tank cap position recognition module is respectively connected to the target vehicle information detection module and the fuel tank cap opening control module, the insertion posture confirmation module is respectively connected to the target vehicle information detection module, the fuel tank cap opening control module, the database and the refueling confirmation execution module, and the refueling confirmation execution module is connected to the refueling completion reset module.

[0024] The target vehicle information detection module collects a parking image of the target vehicle when the target vehicle enters the gas station and stops at a designated location, identifies the model of the target vehicle, and imports environmental information in the gas station and oil quality detection information in the corresponding oil storage tank at the designated location.

[0025] Specifically, the environmental information includes the detected temperature and detected humidity at each detection time point, wherein the detected temperature is detected by a temperature sensor installed in the corresponding position of the gas station, and the detected humidity is detected by a humidity sensor installed in the corresponding position of the gas station.

[0026] Specifically, the oil detection information includes oil viscosity, current oil level height and rated oil level height, etc., wherein the oil viscosity is detected by an oil viscosity sensor installed in the oil storage cylinder corresponding to the specified position, and the oil level is detected by a liquid level gauge installed in the oil storage cylinder corresponding to the specified position.

[0027] It should be added that the technical details involved in starting the camera to automatically identify the vehicle model include: using a high-resolution camera to capture vehicle images, and using computer vision technology and image processing technology to identify the vehicle model based on the captured vehicle images. Among them, the computer vision technology can specifically use a convolutional neural network CNN.

[0028] In a specific embodiment, the use of computer vision technology and image processing technology to identify vehicle models is a relatively common technical means, and computer vision technology and image processing technology are relatively mature technologies. The specific identification process of using computer vision technology and image processing technology to identify vehicle models and locations will not be repeated.

[0029] The fuel tank cap position recognition module is used to use a target detection algorithm to recognize the fuel tank cap position of the target vehicle and send the fuel tank cap position to the fuel tank cap opening control module.

[0030] In a specific embodiment, when using a target detection algorithm to identify the position of the fuel tank cap of a vehicle, a deep learning model such as YOLO, FasterR-CNN, etc. can be used for target detection. Among them, the target detection algorithm is also a relatively mature algorithm available, and its specific identification process will not be repeated.

[0031] The fuel tank cap opening control module is used to start the robotic arm, and according to the position of the fuel tank cap, plan a motion path to move to the position of the fuel tank cap, and start the tool to unscrew the fuel tank cap.

[0032] It should be added that the robotic arm described in the present invention is a multi-degree-of-freedom robotic arm, and the planned motion path is obtained by planning through a path planning algorithm, wherein the path planning algorithm can specifically select one or more of a variety of algorithms such as the A* algorithm, the Dijkstra algorithm, the Bellman-Ford algorithm, etc. to ensure the precise movement and operation of the robotic arm, and planning through the path planning algorithm is an existing relatively mature technology, and its specific planning process will not be repeated.

[0033] The insertion posture confirmation module is used to automatically identify the position of the fuel tank opening, record the fuel tank opening information, and confirm the target insertion posture information of the fueling gun after the fuel tank cap is unscrewed.

[0034] The fuel tank opening information includes information such as the fuel level in the fuel tank, the height of the fuel tank opening, and an image of the fuel tank opening.

[0035] It should be added that the automatic identification of the fuel tank opening position can be achieved by using a depth camera or a lidar to obtain the three-dimensional position coordinates of the fuel tank opening, and then identifying the position of the fuel tank opening. The automatic identification of the fuel tank opening position is a relatively mature technology available, and the specific identification process will not be described in detail.

[0036] In a specific embodiment, the oil level height in the oil tank can be detected by a sensor device corresponding to a manipulator installed on a robotic arm, and the height of the tank opening and the image of the tank opening are detected by a high-definition camera carried by the manipulator, wherein the sensor device for the oil level height can be one or more oil level height detection sensors such as ultrasonic sensors or infrared sensors.

[0037] Specifically, confirming the target insertion posture information of the fuel gun includes: S1, extracting the oil level height in the fuel tank and the fuel tank opening height from the fuel tank opening information, respectively recorded as and .

[0038] S2. Based on the model of the target vehicle, the rated storage oil level height and the reference refueling insertion depth corresponding to the model of the target vehicle are extracted from the database and recorded as and , set the fuel tank insertion depth limit factor, denoted as .

[0039] S3. Extract the image of the fuel tank port from the fuel tank port information, pre-process the image of the fuel tank port, identify the diameter of the fuel tank port by image recognition technology, and extract the reference insertion depth of the corresponding diameter of the fuel tank port from the database, recorded as .

[0040] It should be added that the preprocessing of the image at the fuel tank port includes but is not limited to image denoising, contrast enhancement, brightness adjustment and other operations. For example, the noise in the image is removed by a filtering algorithm to make the edge of the fuel tank port clearer. By adjusting the contrast and brightness, the features of the fuel tank port are highlighted to facilitate subsequent judgment and improve the accuracy of subsequent analysis.

[0041] S4. Calculate the target insertion depth of the fueling gun, recorded as , .

[0042] S5. Analyze the regularity of the fuel tank opening of the target vehicle based on the preprocessed image of the fuel tank opening, and confirm the parking characteristics of the target vehicle based on the parking image of the target vehicle.

[0043] S6. Based on the regularity of the fuel tank opening and the parking characteristics, determine the target insertion angle of the fueling gun, and use the target insertion angle and the target insertion depth as the target insertion posture information of the fueling gun.

[0044] It should be added that if the insertion angle is not appropriate, the passage between the fuel gun and the fuel tank opening may not be smooth, thus affecting the refueling speed. For example, if the angle is too large, the fuel gun and the inner wall of the fuel tank opening may have greater friction, hindering the flow of fuel. If the angle is too small, the fuel may not flow smoothly, or even backflow. The correct insertion angle can make the fuel gun fit tightly with the fuel tank opening, reducing the risk of fuel leakage. It can also prevent the fuel gun from damaging the vehicle's fuel tank opening.

[0045] It should also be added that if the insertion depth is too shallow, the refueling gun may not be able to fully enter the fuel tank port, thus affecting the accuracy of the refueling amount. In this case, the refueling gun may stop refueling prematurely, resulting in the actual refueling amount being less than the required amount. If the insertion depth is too deep, the refueling gun may touch the bottom of the fuel tank or other internal structures, affecting the flow of fuel and even damaging the fuel tank or refueling gun. At the same time, too deep an insertion may also cause the refueling gun to misjudge the refueling amount, causing the refueling amount to exceed the required amount. Therefore, the insertion angle and insertion depth are selected as the main control postures of the refueling process.

[0046] Further, the setting of the oil tank insertion depth limit factor in step S2 includes: S21, calculating the oil level margin limit ratio , .

[0047] S22, calculate the fuel tank opening height limit ratio , , is the set reference fuel tank height.

[0048] It should be added that the fuel tank opening height refers to the height of the fuel tank opening relative to the ground. Fuel is affected by gravity in the fuel tank. The higher the position of the fuel tank opening is, the easier it is for the fuel to flow out. At the same time, when the position of the fuel tank opening is higher, the air pressure in the fuel tank will be relatively low, which is conducive to the flow of fuel. Therefore, the higher the position of the fuel tank opening is, the shallower the depth that the refueling gun needs to be inserted is, that is, the higher the position of the fuel tank opening is, the greater the height restriction ratio of the fuel tank opening is.

[0049] It should also be added that the height of the fuel tank opening from the ground is kept between 1.0 m and 1.5 m for the most convenient operation. For example, The value can be 1.5 meters.

[0050] S23, setting weights of the oil level margin limit ratio and the fuel tank height limit ratio, and obtaining the fuel tank insertion depth limit factor by weighted summation.

[0051] It should be added that the vehicle's oil level is directly related to the safety and effectiveness of the refueling process. If there is a certain amount of fuel in the vehicle's tank, there may be a risk of overflow during refueling. Therefore, it is very important to ensure that the refueling gun is not inserted too deep to avoid overflow, and the height of the tank port directly affects the insertion depth of the refueling gun. The higher the position of the tank port, the shallower the depth the refueling gun needs to be inserted, that is, the height of the tank determines the maximum depth that the refueling gun can be inserted, but its impact is relatively small. Therefore, controlling fuel overflow, ensuring safety, and preventing environmental pollution during automatic refueling are the top priorities. Therefore, when setting the insertion depth limit factor, the weight of the oil level limit ratio is set to be higher than the weight of the tank height limit ratio to avoid potential problems caused by overflow, and illustratively, the weights of the oil level limit ratio and the tank height limit ratio can be taken as 0.7 and 0.3 respectively.

[0052] The embodiment of the present invention comprehensively considers the oil level remaining limit ratio and the fuel tank height limit ratio, and then sets the fuel tank insertion depth limit factor, which can effectively prevent overflow during refueling, thereby reducing pollution to the environment and potential fire risks, and improving the safety and adaptability of refueling posture settings. At the same time, it optimizes the filling efficiency of automatic refueling and reduces the risk of failure during the automatic refueling process.

[0053] Furthermore, regarding the analysis of the regularity of the fuel tank opening of the target vehicle in step S5, it includes: E1, applying an edge detection algorithm to the preprocessed image of the fuel tank opening, thereby extracting the contour of the edge area of ​​the fuel tank opening, and cropping the edge area image from the preprocessed image of the fuel tank opening.

[0054] In a specific embodiment, the edge detection algorithm includes a Canny edge detection algorithm, a Sobel operator, a Roberts operator, etc. Exemplarily, the present invention may select the Canny edge detection algorithm as the edge detection algorithm described in the present invention.

[0055] E2. Calculate the wear degree of the corresponding fuel tank port of the target vehicle, recorded as .

[0056] E3. Extract the area of ​​the edge region corresponding to the fuel tank opening, and calculate the minimum circumscribed circle area of ​​the edge region corresponding to the fuel tank opening. Compare the two, and use the ratio of the two as the circularity of the fuel tank opening, recorded as .

[0057] E4. Calculate the minimum circumscribed rectangular area of ​​the edge area corresponding to the fuel tank opening. Confirm the rectangularity of the fuel tank opening in the same way as the circularity of the fuel tank opening, and record it as ;

[0058] It should be added that the minEnclosingCircle and boundingRect functions of OpenCV can be used to calculate the circumscribed circle and circumscribed rectangle.

[0059] E5. Calculate the regularity of the target vehicle's fuel tank opening , , To set the reference wear.

[0060] In a specific embodiment, The specific value can be 0.3.

[0061] It can be understood that the step E2 of calculating the wear degree of the fuel tank opening of the target vehicle includes E21, graying the edge area image, and calculating the grayscale histogram of the fuel tank opening area.

[0062] In a specific embodiment, the grayscale histogram of the fuel tank opening area may be calculated by using the calcHist function of OpenCV.

[0063] E22. Extract the initial grayscale histogram of the fuel tank opening edge corresponding to the target vehicle model from the database, compare the grayscale histogram of the fuel tank opening area with the initial grayscale histogram, and calculate the grayscale level matching ratio, which is recorded as .

[0064] E23. Select multiple windows in the edge area image, calculate the average grayscale value and standard deviation in each window, and use the ratio of the standard deviation to the average grayscale value as the grayscale change degree.

[0065] E23. The windows with grayscale change greater than the set grayscale change are recorded as difference windows. The number of difference windows is counted and divided by the number of windows. The ratio is taken as the grayscale difference ratio. .

[0066] E24. Filter out the maximum difference change from the grayscale change of each difference window and record it as , calculate the wear degree of the corresponding fuel tank port of the target vehicle , , , and They are the grayscale matching ratio, grayscale difference ratio and difference variation of the set reference respectively.

[0067] In a specific embodiment, illustratively, The possible value is 0.8. The value can be 0.1. The value can be 0.2.

[0068] It should be added that the ratio of the standard deviation to the average gray value reflects the degree of change in the gray value. The greater the change in the gray value, the more directly related it is to wear. In image processing, the change in gray value can reflect the surface unevenness and texture characteristics. For metal surfaces such as the fuel tank port, wear can cause scratches, dents, corrosion, etc. on the surface, which will increase the change in gray value. Therefore, the gray value change is also selected as a wear assessment factor.

[0069] Regarding the statistical grayscale matching ratio in step E22, a histogram comparison method, such as chi-square distance, correlation, intersection, etc., can be used to calculate the similarity between the two, and the similarity is used as the grayscale matching ratio. Among them, the use of the histogram comparison method is a relatively mature means, and its specific calculation process will not be shown here.

[0070] In a specific embodiment, the grayscale level matching ratio can also be statistically analyzed in a customized manner. When the customized statistical method is used, the example statistical process includes: D1, extracting each grayscale level that appears from the grayscale histogram of the fuel tank port area as each current grayscale level, and extracting the number of occurrence areas of each grayscale level of each current grayscale level as the number of current occurrence areas.

[0071] D2. Each gray level appearing in the initial gray level histogram is recorded as each initial gray level, and the number of initial appearance regions corresponding to each initial gray level is extracted.

[0072] D3. Compare each current grayscale level with each initial grayscale level, count the number of identical grayscale levels, and compare it with the current number of grayscale levels in the fuel tank port area. The ratio is used as the initial grayscale level matching ratio, recorded as .

[0073] D4. The same gray level is recorded as the same gray level. The difference between the number of regions with the same gray level and the initial number of regions is calculated. The absolute value of the difference is taken as the difference in the number of regions with the same gray level. The average difference in the number of regions with the same gray level is calculated to obtain the average difference in the number of regions with the same gray level, which is recorded as .

[0074] D5. Filter out the minimum initial gray level from each initial gray level, and count the number of current gray levels whose gray levels are lower than the minimum initial gray level, recorded as .

[0075] D6. Statistical gray level matching ratio , , is a natural constant, To set the reference occurrence area number difference, To set the grayscale reduction ratio for reference.

[0076] In a specific embodiment, The specific value can be 2. The value can be 1, and the matching ratio Is After reorganization, we get: It represents the matching ratio correction factor, which confirms the degree of grayscale difference by two dimensions: the number of grayscale difference areas and the number of grayscale difference levels, and sets the matching ratio correction factor according to the degree of grayscale difference, so as to reduce the error of grayscale level matching ratio only from the grayscale level matching ratio level, thereby ensuring the representativeness and accuracy of the grayscale level matching ratio setting.

[0077] It should be added that the number of windows is determined by the set window size. Under normal circumstances, the window size can be 5x5 or 10x10. If the edge area image is larger or the resolution is lower, 10x10 can be used. If the edge area image is smaller or the resolution is higher, 5x5 can be used. Among them, the definition of the size of the edge area image and the definition of the resolution mainly depend on the conventional definition. For example, if the number of pixels is less than or equal to 100 pixels, the edge area image can be defined as smaller, and if the number of pixels exceeds 100 pixels, the edge area image can be defined as larger. The resolution usually refers to the amount of information contained per unit area in the image. When the number of pixels per inch is less than or equal to 100, the resolution is defined as lower, and when the number of pixels per inch exceeds 100, the resolution is defined as higher.

[0078] Furthermore, regarding confirming the parking features of the target vehicle in step S5, it includes: R1, extracting the edge contour of the target vehicle from the parking image through an edge detection algorithm, detecting the straight line features in the parking image through a straight line detection algorithm, and determining a reference plane in the parking image.

[0079] It should be added that the straight line detection algorithm includes Hough transform, etc., and Hough transform can be specifically selected for detection. The straight line detection algorithm is a relatively mature algorithm currently available, and its specific detection process is not described here. The edge of the vehicle usually contains some straight line features, such as the edge of the wheel, the side of the body, etc.

[0080] R2. Determine the longitudinal axis of the target vehicle based on the extracted straight line features, compare the vehicle axis with the reference plane, and calculate the tilt angle of the target vehicle through a geometric algorithm .

[0081] It should be supplemented that the longitudinal axis of the vehicle body can be determined by fitting a straight line or calculating the average direction of the straight lines.

[0082] It should also be added that a reference plane is determined in the image, and the ground or other known horizontal objects can usually be selected as a reference. The reference plane can be determined by detecting horizontal straight lines in the image or by using known object sizes and positions.

[0083] Exemplarily, the geometric algorithm includes geometric algorithms such as dot product and cross product of vectors. Exemplarily, the direction vector of the longitudinal axis of the target vehicle is recorded as , the normal vector of the reference plane is recorded as , then the vehicle's tilt angle The formula is: .

[0084] R3. Based on the parking image, determine the center point position and parking direction of the target vehicle, and simultaneously confirm the center point position and parking direction of the fuel gun.

[0085] It should be added that the center position and parking direction of the vehicle can be determined by calculating the center of mass of the vehicle outline or fitting a rectangular frame of the vehicle, and the parking direction of the vehicle can be determined by analyzing the vehicle outline or the parking of the license plate. The center position and main direction of the fuel pump can be determined by calculating the center of mass of the fuel pump outline or analyzing the structure of the fuel pump, and the main direction of the fuel pump can be determined by the installation direction of the fuel pump or the direction of the fuel gun.

[0086] R4, record the center position coordinates of the vehicle and the tanker as and , the parking directions of the vehicle and the tanker are represented by vectors, respectively, and .

[0087] R5. Calculate the angle between the line connecting the center position of the target vehicle and the center position of the fuel dispenser and the horizontal direction , .

[0088] R6. Calculate the angle between the target vehicle direction and the fuel dispenser parking direction , .

[0089] R7, set the weight of the center position and parking direction, and Perform weighted summation to obtain the relative angle between the vehicle and the tanker ,Will and As the parking features of the target vehicle.

[0090] It should be added that when considering automatic refueling operation, the alignment of the refueling gun with the vehicle tank port is more dependent on whether the parking direction of the vehicle and the refueling machine matches well. Therefore, a higher weight coefficient is given to this angle, and an exemplary value can be 0.6. The angle between the line between the center position of the target vehicle and the center position of the refueling machine and the horizontal direction is relatively less important, and an exemplary value can be 0.4.

[0091] Furthermore, the step S6 of confirming the target insertion angle of the fueling gun includes: S61, matching and comparing the regularity of the fuel tank opening with the regularity intervals corresponding to the preset regularity levels to obtain a matching regularity level.

[0092] S62. Based on the matching regularity level, define an insertion angle adjustment value, denoted as .

[0093] It should be added that in a specific embodiment, the regularity of the fuel tank opening can be specifically divided into three levels: high, medium and low, and the corresponding defined insertion angle adjustment values ​​can be respectively set to , and .

[0094] S63, setting the weights of the tilt angle of the target vehicle and the relative angle between the vehicle and the fuel dispenser, respectively and , .

[0095] In a specific embodiment, the tilt angle of the target vehicle has a greater impact on the insertion angle. Although it can be adjusted to a certain extent, the adjustment is difficult. At the same time, the tilt angle data is relatively reliable, so it is given a lower weight. For example, The value is 0.4, and the relative angle directly determines the initial direction of the oil gun and has an important influence on the insertion angle. In the automatic refueling system, the oil gun can be adjusted to adapt to the relative angle, which has a certain degree of adjustability. At the same time, the relative angle data can also be measured and calculated more accurately, so it is given a higher weight. For example, The value is 0.6.

[0096] S64, calculate the target insertion angle of the fueling gun , .

[0097] The embodiment of the present invention controls the insertion of the fuel gun into the fuel tank port by confirming the target insertion posture information of the fuel gun, thereby effectively solving the current problem of insufficient attention to the preparatory control before automatic refueling of the vehicle. It fully considers the influence of the vehicle posture and the refueling posture, and realizes the refined control of the corresponding posture of the fuel gun, thereby ensuring the stability of the refueling process and the reliability of the oil quantity control.

[0098] The refueling confirmation execution module is used to control the refueling gun to be inserted into the fuel tank port based on the target insertion posture information of the refueling gun, and at the same time import the set refueling amount of the target vehicle, and confirm the appropriate refueling index, and start the refueling pump to refuel according to the appropriate refueling index.

[0099] Specifically, confirming the suitable refueling index includes: F1, extracting the detection temperature and the detection humidity at each detection time point from the environmental information.

[0100] F2. Extract the oil viscosity from the oil detection information in the oil storage cylinder at the specified position, and record it as , extract the current oil level and the rated oil level at the same time, and take the ratio of the current oil level to the rated oil level as the oil level ratio, recorded as .

[0101] F3. Compare the difference between the rated storage oil level and the oil level in the tank with the rated storage oil level to obtain the ratio of the amount of oil to be replenished and set the refueling correction factor.

[0102] F4. Extract the default pumping pressure of the refueling gun, correct the default pumping pressure by the refueling setting correction factor, and use the corrected pumping pressure as the appropriate refueling indicator.

[0103] Specifically, the corrected pumping pressure = default setting pumping pressure × (1 + refueling setting correction factor)

[0104] Furthermore, the refueling setting correction factor is set, including: F31, statistical refueling environment interference, recorded as .

[0105] F32, will and As the evaluation variable, the statistical oil body state interference degree is obtained by linear regression function statistics, which is recorded as .

[0106] It should be added that the specific statistical formula of the linear regression function of the oil body state interference is as follows: , and The reference interference pumping viscosity and interference pumping oil level height ratio are set respectively.

[0107] In a specific embodiment, The value is 0.8 square millimeters per second. The value is 0.6.

[0108] F33, record the oil volume ratio to be replenished as , and are compared with the set first interference oil quantity ratio to be replenished and the second interference oil quantity ratio to be replenished, and the first interference oil quantity ratio to be replenished and the second interference oil quantity ratio to be replenished are recorded as and , .

[0109] In a specific embodiment, The value can be 0.7. The value can be 0.2.

[0110] F34, if , the oil replenishment interference is recorded as 0, if ,Will As the supplementary oil quantity disturbance, it is recorded as ,like ,Will As the supplementary oil quantity disturbance, it is recorded as , and thus obtain the oil replenishment interference , The value is 0 or or .

[0111] It should be added that when the remaining oil in the vehicle's fuel tank is small, the space inside the fuel tank is relatively large, and the oil is likely to generate a large impact force and fluctuation after entering the vehicle's fuel tank. If the pumping pressure is too high, the oil enters the vehicle's fuel tank at a greater speed and force, which may hit the inner wall of the fuel tank or cause oil splashing, which may not only cause oil waste, but also generate safety hazards such as static electricity. In this case, a higher pumping pressure may cause the pressure in the vehicle's fuel tank to rise rapidly, causing a certain amount of pressure on the vehicle's fuel tank structure. When the remaining oil in the vehicle's fuel tank is medium or large, the space inside the vehicle's fuel tank is very small, and the pressure is likely to rise rapidly when the oil enters. Excessive pressure may damage the vehicle's fuel tank, refueling pipeline and related components, and it is also easy to cause oil to overflow from the vehicle's fuel tank port. Therefore, a comprehensive analysis is required from both ends, and the supplementary oil interference is a negative correction indicator, that is, the greater the supplementary oil interference, the smaller the corresponding refueling setting correction factor, and the smaller the need to increase the pumping pressure setting.

[0112] F35, set the refueling correction factor, recorded as , , is the set reference oil state interference degree.

[0113] Furthermore, in step F31, the interference degree of the refueling environment is counted, including: selecting the lowest temperature from the detected temperatures at each detection time point, recorded as , and calculate the standard deviation of the detected temperature at each detection time point, and record the calculation result as .

[0114] The maximum humidity is selected from the detected humidity at each detection time point and recorded as , and calculate the standard deviation of the detected humidity at each detection time point, and record the calculation result as .

[0115] Statistics on the interference of the refueling environment , , and They are the reference interference temperature and interference humidity.

[0116] It should be added that temperature changes will significantly affect the viscosity of oil products. When the temperature rises, the viscosity of the oil decreases and the fluidity increases. This means that at higher temperatures, the pressure required to pump the oil will decrease, and when the temperature decreases, the oil becomes more viscous and the fluidity becomes worse. At this time, in order to ensure the normal pumping speed, the pumping pressure needs to be increased. In a high humidity environment, the moisture in the air is easily mixed into the oil, especially for some oils with strong hydrophilicity. When the water and the oil are fully mixed, an emulsion will be formed. The viscosity of the emulsified oil will change, usually increasing, which makes the fluidity of the oil worse, that is, the pumping pressure needs to be increased. Therefore, the lowest temperature and the highest humidity are selected as the main evaluation environmental indicators for increasing the pumping pressure. They are positive correction indicators, that is, the greater the interference of the refueling environment, the larger the corresponding refueling setting correction factor.

[0117] It should be added that the purpose of calculating the standard deviation of the detected temperature and the standard deviation of the detected humidity is to set the corresponding correction factors when performing temperature analysis and humidity analysis. represents the temperature correction factor, Represents the humidity correction factor to ensure the reliability of the corresponding analysis results during temperature analysis and humidity analysis.

[0118] In a specific embodiment, generally speaking, when the temperature is too low and close to the freezing point of the oil, it will cause obvious interference to the pumping. For example, when the temperature is below 0°C or even lower, its fluidity will be greatly reduced, so 0°C is selected as The specific value of relative humidity is usually above 70%, which will begin to have a certain impact on the pumping of the oil. As the humidity continues to rise, the impact will gradually increase. When the moisture content in the air is high, the possibility of oil absorbing moisture is greatly increased, which is easy to cause problems such as oil emulsification and equipment corrosion, and the interference with pumping is more obvious. Therefore, 70% is selected as The specific value of .

[0119] The embodiment of the present invention realizes multi-dimensional comprehensive detection by comprehensively confirming the parking characteristics of the target vehicle and considering the oil level height in the vehicle's fuel tank and the oil quality detection information in the corresponding oil storage cylinder at the designated position, thereby making up for the deficiency of the current lack of vehicle status inspection, facilitating the improvement of the targetedness of subsequent automated refueling control, and at the same time ensuring the standardization and flexibility of automated refueling.

[0120] The database is used to store the rated storage oil level height and reference refueling insertion depth designed for each vehicle model, store the reference insertion depth of each tank port diameter, and store the initial grayscale histogram of the tank port edge corresponding to each vehicle model.

[0121] The refueling completion reset module is used to stop the refueling pump and pull out the refueling gun from the fuel tank port after refueling is completed. Then, the mechanical arm uses a tool to tighten the fuel tank cap and reset the mechanical arm and the refueling gun.

[0122] The embodiment of the present invention realizes the automation of the entire process from the vehicle entering the gas station to the completion of refueling through the collaborative work of multiple modules, ensuring the efficient, safe and reliable operation of vehicle refueling, which not only improves the operating efficiency of the gas station, but also enhances the user experience and reduces human errors and safety hazards.

[0123] 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. An automatic refueling control system based on artificial intelligence, characterized in that: The system includes: The target vehicle information detection module collects the parking image of the target vehicle when the target vehicle enters the gas station and stops at the designated location, identifies the model of the target vehicle, and imports the environmental information in the gas station and the oil detection information in the corresponding oil storage tank at the designated location; A fuel tank cap position recognition module, used to use a target detection algorithm to recognize the position of the fuel tank cap of the target vehicle and send the fuel tank cap position to the fuel tank cap opening control module; The fuel tank cap opening control module is used to start the robot arm, and according to the position of the fuel tank cap, plan the motion path to move to the position of the fuel tank cap, and start the tool to unscrew the fuel tank cap; Insertion posture confirmation module, used to automatically identify the position of the fuel tank opening, record the fuel tank opening information, and confirm the target insertion posture information of the fuel gun after the fuel tank cap is unscrewed; The refueling confirmation execution module is used to control the refueling gun to be inserted into the fuel tank port based on the target insertion posture information of the refueling gun, import the set refueling amount of the target vehicle, and confirm the appropriate refueling index. According to the appropriate refueling index, the refueling pump is started to refuel; A database for storing the rated storage oil level height and reference refueling insertion depth designed for each vehicle model, storing the reference insertion depth of each fuel tank opening diameter, and storing the initial grayscale histogram of the fuel tank opening edge corresponding to each vehicle model; The refueling completion reset module is used to stop the refueling pump and pull out the refueling gun from the fuel tank port after refueling is completed. Then, the robotic arm uses a tool to tighten the fuel tank cap and reset the robotic arm and the refueling gun.

2. The artificial intelligence-based automatic refueling control system according to claim 1, characterized in that: The confirmation of the target insertion posture information of the refueling gun includes: The oil level in the tank and the height of the tank opening are extracted from the tank opening information and recorded as and ; Based on the model of the target vehicle, the rated storage oil level height and the reference refueling insertion depth corresponding to the model of the target vehicle are extracted from the database and recorded as and , set the fuel tank insertion depth limit factor, denoted as ; The image of the fuel tank port is extracted from the fuel tank port information, the image of the fuel tank port is preprocessed, the diameter of the fuel tank port is identified by image recognition technology, and the reference insertion depth corresponding to the diameter of the fuel tank port is extracted from the database, which is recorded as ; Calculate the target insertion depth of the fuel gun, denoted as , ; Based on the pre-processed image of the fuel tank opening, the regularity of the fuel tank opening of the target vehicle is analyzed, and based on the parking image of the target vehicle, the parking characteristics of the target vehicle are confirmed; Based on the regularity of the fuel tank opening and the parking characteristics, the target insertion angle of the fueling gun is determined, and the target insertion angle and target insertion depth are used as the target insertion posture information of the fueling gun.

3. The automatic refueling control system based on artificial intelligence according to claim 2 is characterized in that: The step of setting the oil tank insertion depth limit factor includes: Calculate the oil level limit ratio , ; Calculate the fuel tank opening height limit ratio , , is the set reference fuel tank height; The weights of the oil level margin limit ratio and the fuel tank height limit ratio are set, and the fuel tank insertion depth limit factor is obtained by weighted summation.

4. The automatic refueling control system based on artificial intelligence according to claim 2 is characterized in that: The step of analyzing the regularity of the fuel tank opening of the target vehicle includes: Applying an edge detection algorithm to the preprocessed image of the fuel tank opening, thereby extracting the contour of the edge area of ​​the fuel tank opening, and cutting out the edge area image from the preprocessed image of the fuel tank opening; Calculate the wear degree of the corresponding fuel tank port of the target vehicle, recorded as ; Extract the area of ​​the edge area corresponding to the fuel tank opening, and calculate the minimum circumscribed circle area of ​​the edge area corresponding to the fuel tank opening. Compare the two and use the ratio of the two as the circularity of the fuel tank opening, recorded as ; Calculate the minimum circumscribed rectangular area of ​​the edge area corresponding to the fuel tank opening, and confirm the rectangularity of the fuel tank opening in the same way as the circularity of the fuel tank opening, which is recorded as ; Calculate the regularity of the target vehicle's fuel tank opening , , To set the reference wear, is a natural constant.

5. The automatic refueling control system based on artificial intelligence according to claim 4 is characterized in that: The calculating the wear degree of the fuel tank opening corresponding to the target vehicle includes: Grayscale the edge area image and calculate the grayscale histogram of the fuel tank mouth area; Extract the initial grayscale histogram of the fuel tank opening edge corresponding to the target vehicle model from the database, compare the grayscale histogram of the fuel tank opening area with the initial grayscale histogram, and calculate the grayscale level matching ratio, which is recorded as ; Select multiple windows in the edge area image, calculate the average gray value and standard deviation in each window, and use the ratio of the standard deviation to the average gray value as the grayscale change; The windows with grayscale change greater than the set grayscale change are recorded as difference windows. The number of difference windows is counted and divided by the number of windows. The ratio is taken as the grayscale difference ratio. ; The maximum difference change degree is selected from the grayscale change degrees of each difference window and recorded as , calculate the wear degree of the corresponding fuel tank port of the target vehicle , , , and They are the grayscale matching ratio, grayscale difference ratio and difference variation of the set reference respectively.

6. The automatic refueling control system based on artificial intelligence according to claim 2 is characterized in that: The step of confirming the parking characteristics of the target vehicle includes: Extracting the edge contour of the target vehicle from the parking image by using an edge detection algorithm, detecting the straight line features in the parking image by using a straight line detection algorithm, and determining a reference plane in the parking image; Based on the extracted straight line features, the longitudinal axis of the target vehicle is determined, the vehicle axis is compared with the reference plane, and the tilt angle of the target vehicle is calculated through a geometric algorithm. ; Based on the parking image, determine the center point position and parking direction of the target vehicle, and simultaneously confirm the center point position and parking direction of the fuel gun; The center coordinates of the vehicle and the tanker are recorded as and , the parking directions of the vehicle and the tanker are represented by vectors, respectively, and ; Calculate the angle between the line connecting the center position of the target vehicle and the center position of the refueling machine and the horizontal direction , ; Calculate the angle between the target vehicle direction and the fuel dispenser parking direction , ; Set the weights of the center position and parking direction. and Perform weighted summation to obtain the relative angle between the vehicle and the tanker ,Will and As the parking features of the target vehicle.

7. The artificial intelligence-based automatic refueling control system according to claim 6 is characterized in that: The step of confirming the target insertion angle of the fueling gun includes: The regularity of the fuel tank port is matched and compared with the regularity intervals corresponding to the preset regularity levels to obtain the matching regularity level; Based on the matching regularity level, define the insertion angle adjustment value, denoted as ; The weights of the target vehicle’s tilt angle and the relative angle between the vehicle and the tanker are set as and , ; Calculate the target insertion angle of the fuel nozzle , .

8. The automatic refueling control system based on artificial intelligence according to claim 2 is characterized in that: The indicators for confirming the suitability of refueling include: Extracting the detection temperature and the detection humidity at each detection time point from the environmental information; The oil viscosity is extracted from the oil detection information in the corresponding oil storage cylinder at the specified position, and recorded as , extract the current oil level and the rated oil level at the same time, and take the ratio of the current oil level to the rated oil level as the oil level ratio, recorded as ; The difference between the rated storage oil level and the oil level in the oil tank is compared with the rated storage oil level to obtain the ratio of the amount of oil to be replenished, and the refueling setting correction factor is set; The default pumping pressure of the refueling gun is extracted, and the default pumping pressure is corrected by the refueling setting correction factor, and the corrected pumping pressure is used as the appropriate refueling indicator.

9. The artificial intelligence-based automatic refueling control system according to claim 8, characterized in that: The refueling correction factor setting includes: Statistical refueling environment interference, denoted as ; Will and As the evaluation variable, the statistical oil body state interference degree is obtained by linear regression function statistics, which is recorded as ; The ratio of oil to be replenished is recorded as , and are compared with the set first interference oil quantity ratio to be replenished and the second interference oil quantity ratio to be replenished, and the first interference oil quantity ratio to be replenished and the second interference oil quantity ratio to be replenished are recorded as and , ; like , the oil replenishment interference is recorded as 0, if ,Will As the supplementary oil quantity disturbance, it is recorded as ,like ,Will As the supplementary oil quantity disturbance, it is recorded as , and thus obtain the oil replenishment interference , The value is 0 or or ; Set the refueling correction factor, denoted as , , is the set reference oil state interference degree.

10. The automatic refueling control system based on artificial intelligence according to claim 8, characterized in that: The statistical refueling environment interference degree includes: The lowest temperature is selected from the detected temperatures at each detection time point and recorded as , and calculate the standard deviation of the detected temperature at each detection time point, and record the calculation result as ; The maximum humidity is selected from the detected humidity at each detection time point and recorded as , and calculate the standard deviation of the detected humidity at each detection time point, and record the calculation result as ; Statistics on the interference of the refueling environment , , and They are the reference interference temperature and interference humidity.

Images