Hydraulic medium leakage detection method and system for automatic wharf AGV

Abstract

The invention discloses a hydraulic medium leakage detection method and system for an automatic wharf AGV. A first camera and a second camera which are installed at the front end and the rear end of the AGV are used for obtaining a first road surface image and a second road surface image in the driving period of the AGV; constructing a space state equation during the driving period of the AGV, and calculating the position difference and the driving deflection angle of the AGV when the first camera and the second camera shoot the same road surface position based on the space state equation; correcting the first road surface image and the second road surface image based on the position difference and the driving deflection angle; and comparing the corrected first pavement image with the corrected second pavement image to judge whether the hydraulic medium leaks or not. Compared with an existing mode of detecting the liquid level difference through a liquid level instrument to judge whether the hydraulic equipment leaks or not, the method has the technical advantages of being high in detection real-time performance, high in detection sensitivity and low in cost.

Description

Technical Field

[0001] The present invention belongs to the technical field of automatic guided vehicle fault detection, and in particular, relates to a hydraulic medium leakage detection method and system for an automated terminal AGV. Background Art

[0002] AGV (Automated Guided Vehicle) is a key equipment for horizontal container transportation between bridge cranes and rail cranes at automated terminals. At present, the lifting mechanism used by AGVs at automated terminals for container interaction and the steering and braking mechanism used when the vehicle is moving generally use hydraulic systems, which have the advantages of light weight, flexible layout and easier equipment automation.

[0003] However, due to the complex flow of hydraulic system fluid and the difficulty in ensuring the sealing accuracy of hydraulic components, the hydraulic system of AGV has hydraulic oil leakage problems during long-term operation. Severe hydraulic oil leakage not only affects the operating status of a single AGV device, but also seriously affects the production operations of the entire terminal. Summary of the invention

[0004] The purpose of the present invention is to provide a hydraulic medium leakage detection method and system for an automated terminal AGV, so as to realize real-time fault identification and alarm for the medium leakage problem of the hydraulic system of the automated terminal AGV.

[0005] The present invention is implemented by the following technical solutions:

[0006] A hydraulic medium leakage detection system for automated terminal AGV is proposed, comprising:

[0007] A road surface image acquisition unit, composed of a first camera and a second camera installed at the front and rear ends of the AGV, for respectively acquiring a first road surface image and a second road surface image during the driving of the AGV;

[0008] A spatial observation unit, used to construct a spatial state equation during the driving of the AGV, and to calculate the position difference and driving deflection angle of the AGV when the first camera and the second camera shoot the same road position based on the spatial state equation;

[0009] a correction unit, configured to correct the first road surface image and the second road surface image based on the position difference and the driving deflection angle;

[0010] The leakage detection unit is used to compare the corrected first road surface image with the second road surface image to determine whether the hydraulic medium is leaking.

[0011] In some embodiments of the present invention, the space observation unit constructs the space state equation during AGV driving using the following steps:

[0012] Construct the discrete state equations of the AGV's lateral velocity, lateral displacement, longitudinal velocity, and longitudinal displacement:

[0013] ;in, is the displacement in the X direction at the kth moment, is the velocity in the X direction at the kth moment, is the displacement in the Y direction at the kth moment, is the speed in the Y direction at the kth moment, T corresponds to the sampling time of the vehicle antenna and the vehicle speed sensor, and They are the accelerations in the X and Y directions provided by the AGV walking mechanism. and They are the operating noise interference caused by the AGV operation conditions;

[0014] Establish the observation equation: ;in, The measured values ​​of the sensors are collected for information, , , , are the observation noise of the information acquisition sensor respectively;

[0015] The discrete state equation and the observation equation are combined to obtain a set of spatial state equations.

[0016] In some embodiments of the present invention, the spatial observation unit measures the driving position and driving speed of the AGV based on the spatial state equation group; calculates the lateral position difference of the AGV when the first camera and the second camera shoot the same road position. , longitudinal position difference , and the driving deflection angle .

[0017] In some embodiments of the present invention, the leakage detection unit determines whether the hydraulic medium is leaking through the following steps: using the HSV color model, extracting pixel points that match the color of the hydraulic oil from the first road surface image and the second road surface image; calculating the difference between the pixel points extracted from the first road surface image and the pixel points extracted from the second road surface image; and determining that the hydraulic medium is leaking when the pixel point difference is greater than a threshold.

[0018] In some embodiments of the present invention, the system further comprises: an obstacle avoidance unit, which is used to prohibit the AGV from running and control other AGVs to avoid obstacles when the leakage detection unit determines that the hydraulic medium is leaking.

[0019] A method for detecting hydraulic medium leakage of AGV in an automated terminal is proposed, comprising:

[0020] Acquire a first road surface image and a second road surface image during the driving of the AGV by using a first camera and a second camera installed at the front and rear ends of the AGV;

[0021] Constructing a spatial state equation during the driving of the AGV, and calculating the position difference and driving deflection angle of the AGV when the first camera and the second camera shoot the same road position based on the spatial state equation;

[0022] correcting the first road surface image and the second road surface image based on the position difference and the travel deflection angle;

[0023] The corrected first road surface image and the second road surface image are compared to determine whether the hydraulic medium is leaking.

[0024] In some embodiments of the present invention, the following steps are used to construct the spatial state equation during AGV driving:

[0025] Construct the discrete state equations of the AGV's lateral velocity, lateral displacement, longitudinal velocity, and longitudinal displacement:

[0026] ;in, is the displacement in the X direction at the kth moment, is the velocity in the X direction at the kth moment, is the displacement in the Y direction at the kth moment, is the speed in the Y direction at the kth moment, T corresponds to the sampling time of the vehicle antenna and the vehicle speed sensor, and They are the accelerations in the X and Y directions provided by the AGV walking mechanism. and They are the operating noise interference caused by the AGV operation conditions;

[0027] Establish the observation equation: ;in, The measured values ​​of the sensors are collected for information, , , , are the observation noise of the sensor respectively;

[0028] The discrete state equation and the observation equation are combined to obtain a set of spatial state equations.

[0029] In some embodiments of the present invention, the position difference and driving deflection angle of the AGV when the first camera and the second camera shoot the same road position are calculated based on the spatial state equation, including: measuring the driving position and driving speed of the AGV based on the spatial state equation group; calculating the lateral position difference of the AGV when the first camera and the second camera shoot the same road position , longitudinal position difference , and the driving deflection angle .

[0030] In some embodiments of the present invention, the following steps are used to determine whether the hydraulic medium is leaking: using the HSV color model, pixels that match the color of the hydraulic oil are extracted from the first road surface image and the second road surface image; calculating the difference between the pixels extracted from the first road surface image and the pixels extracted from the second road surface image; and determining that the hydraulic medium is leaking when the pixel difference is greater than a threshold.

[0031] In some embodiments of the present invention, the method further includes: setting the hydraulic oil color threshold based on the color of the AGV driving field or environmental information.

[0032] Compared with the prior art, the advantages and positive effects of the present invention are:

[0033] 1. Compared with the prior art method of using a liquid level meter to detect the liquid level difference to determine whether the AGV hydraulic equipment is leaking, the present invention can implement real-time detection of whether the hydraulic medium is leaking on the running device through image acquisition, making the equipment operation safer.

[0034] 2. Compared with the prior art which uses a liquid level meter to detect the liquid level difference to determine whether the AGV hydraulic equipment is leaking, but has the problem of difficulty in identifying oil leakage faults, the present invention can modify the sensitivity of AGV hydraulic medium leakage detection by changing the hydraulic oil color threshold, and accurately detect small-scale oil leakage faults.

[0035] 3. The present invention only needs two cameras to collect two road surface images, and can realize leakage judgment by combining the existing position sensor and wheel speed sensor of AGV, which has higher economy and universality.

[0036] Other features and advantages of the present invention will become more apparent after reading the detailed description of the embodiments of the present invention in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are part of the present invention and are used to provide a further understanding of the present invention. The exemplary embodiments and descriptions of the present invention are used to explain the present invention, but do not constitute an improper limitation of the present invention. Obviously, the accompanying drawings described below are only some embodiments. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0038] Figure 1 This is a schematic diagram of the system architecture of the hydraulic medium leakage detection system for automated terminal AGV proposed by the present invention;

[0039] Figure 2The steps of the hydraulic medium leakage detection method for automated terminal AGV proposed by the present invention are schematically shown;

[0040] Figure 3 This is a schematic diagram of the image correction principle in the hydraulic medium leakage detection method for automated terminal AGV proposed by the present invention;

[0041] Figure 4 It is a schematic diagram of the identification diagram of the hydraulic medium leakage detection method for automated terminal AGV proposed by the present invention.

[0042] It should be noted that these drawings and textual descriptions are not intended to limit the conceptual scope of the present invention in any way, but are intended to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The following embodiments are used to illustrate the present invention but are not used to limit the scope of the present invention.

[0044] like Figure 1 As shown, the hydraulic medium leakage detection system for automated terminal AGV proposed by the present invention is composed of a road surface image acquisition unit 1, a space observation unit 2, a correction unit 3, and a leakage detection unit 4. It is combined with the existing position sensor 5, wheel speed sensor 6, networking unit 7 and obstacle avoidance unit 8 of the AGV equipment to realize the detection, early warning and obstacle avoidance of hydraulic medium leakage.

[0045] Among them, the road surface image acquisition unit 1 is composed of a first camera 11 and a second camera 12 installed at the front and rear ends of the AGV, which are used to respectively acquire the first road surface image and the second road surface image during the driving of the AGV; the first road surface image and the second road surface image are images taken by the first camera and the second camera at the same road surface position during the driving of the AGV.

[0046] The space observation unit 2 is used to construct the space state equation during the driving of the AGV, and calculate the position difference and driving deflection angle of the AGV when the first camera 11 and the second camera 12 shoot the same road surface position based on the space state equation.

[0047] The correction unit 3 is used to correct the first road surface image and the second road surface image based on the position difference and the driving deflection angle so that the two overlap in position and angle.

[0048] The leakage detection unit 4 is used to compare the corrected first road surface image with the second road surface image to determine whether the hydraulic medium is leaking.

[0049] The position sensor 5 is used to obtain the lateral displacement and longitudinal displacement during the travel of the AGV.

[0050] The wheel speed sensor 6 is used to obtain the lateral acceleration and longitudinal acceleration of the AGV during driving.

[0051] The networking unit 7 is connected to the terminal operating system to realize the reporting of the judgment result so that the terminal operating system can implement early warning and rectification for the leakage fault.

[0052] The obstacle avoidance unit 8 is used to perform obstacle avoidance on the AGV and control other AGVs when the leakage detection unit 4 determines that the hydraulic medium is leaking.

[0053] Based on the hydraulic medium leakage detection system, the hydraulic medium leakage detection method for automated terminal AGV proposed by the present invention is as follows: Figure 2 As shown, the following steps are included:

[0054] S1: Acquire a first road surface image and a second road surface image during the driving of the AGV by using a first camera and a second camera installed at the front and rear ends of the AGV.

[0055] The first road surface image and the second road surface image are images captured by the first camera and the second camera at the same road surface position during the driving of the AGV.

[0056] S2: Construct a spatial state equation during the driving of the AGV, and calculate the position difference and driving deflection angle of the AGV when the first camera and the second camera shoot the same road position based on the spatial state equation.

[0057] The spatial observation unit 2 uses the following steps to construct the spatial state equation during AGV driving:

[0058] (1) Construct the discrete state equations of the AGV's lateral velocity, lateral displacement, longitudinal velocity, and longitudinal displacement:

[0059] ;in, is the displacement in the X direction at the kth moment, is the velocity in the X direction at the kth moment, is the displacement in the Y direction at the kth moment, is the Y-direction speed at the kth moment, T corresponds to the sampling time of the position sensor (usually the vehicle-mounted antenna) and the wheel speed sensor, and They are the accelerations in the X and Y directions provided by the AGV walking mechanism. and They are respectively the noise interference caused by the operation of the AGV (equipment deviation, such as the deviation of equipment acceleration caused by a fault in the hydraulic system during the AGV turning, which is a statistical value or empirical value). As mentioned above, the X direction and the Y direction are perpendicular to each other to form a two-dimensional coordinate system, corresponding to the horizontal and vertical directions of the AGV, respectively.

[0060] (2) Establish the observation equation: ;in, The measured values ​​of the sensors are collected for information, , , , They are respectively the observation noise of the information acquisition sensors (position sensor, wheel speed sensor) (the measurement accuracy deviation of the sensor, which is a statistical value or empirical value).

[0061] (3) The discrete state equation and the observation equation are combined to obtain the spatial state equation group.

[0062] After establishing the spatial state equation group, the Kalman filter algorithm is used to filter out noise interference, obtain the actual AGV driving position and driving speed, and calculate the lateral position difference of the AGV when the first camera 11 and the second camera 12 shoot the same road position. , longitudinal position difference , and the driving deflection angle .

[0063] S3: Correct the first road surface image and the second road surface image based on the position difference and the driving deflection angle.

[0064] refer to Figure 3 As shown, the lateral position difference of the AGV when the first camera and the second camera shoot the same road position calculated by S2 is , longitudinal position difference , and the driving deflection angle , in the same coordinate system, the second road surface image is translated and the angle is adjusted so that it is in the same position and direction as the first road surface image.

[0065] S4: Compare the corrected first road surface image and the second road surface image to determine whether the hydraulic medium is leaking.

[0066] The leakage detection unit 4 determines whether the hydraulic medium is leaking through the following steps:

[0067] (1) Using the HSV color model, pixels that match the color of the hydraulic oil are extracted from the first road image and the second road image.

[0068] The present invention adopts the HSV color model (H: hue, S: saturation, V: brightness, where H: 0°~252°, S: 0%~5%, V: 0%~30%), and sets the hydraulic oil color threshold according to the color characteristics of the hydraulic system medium. The hydraulic oil color threshold can be set and modified at the front end of the system based on the color or environmental information of the AGV driving site, and can effectively distinguish the site color changes caused by hydraulic leakage or weather. Figure 4 In the illustrated embodiment of hydraulic medium leakage identification, the image in the middle of a row identifies the oil leakage point or oil seepage spot, while the images on the left and right do not identify the oil leakage point or oil seepage spot.

[0069] (2) Calculate the difference between the pixel points extracted from the first road surface image and the pixel points extracted from the second road surface image.

[0070] If there is no leakage of hydraulic medium, the number of pixel points extracted from the first road surface image and the second road surface image is not much different. If leakage occurs between the time when the first camera obtains the first road surface image at the first road surface position and the time when the AGV drives and causes the second camera to also move to the first road surface position, then the number of pixel points extracted from the second road surface image obtained by the second camera is significantly different from the number of pixel points extracted from the first road surface image.

[0071] (3) When the pixel difference is greater than the threshold, it is judged that the hydraulic medium is leaking.

[0072] The vehicle connection unit 7 sends the judgment result (oil leakage or oil seepage) and the fault image to the terminal operation system, which stores the judgment result and the fault image and provides real-time feedback to the operator. The obstacle avoidance unit 8 prohibits the AGV from running by connecting to the AGV through the base station and controls other operating AGVs to avoid obstacles.

[0073] It should be pointed out that the above description is not a limitation of the present invention, and the present invention is not limited to the above examples. Changes, modifications, additions or substitutions made by ordinary technicians in this technical field within the essential scope of the present invention should also fall within the protection scope of the present invention.

Claims

1. A hydraulic medium leakage detection system for automated terminal AGV, characterized in that: include: A road surface image acquisition unit, composed of a first camera and a second camera installed at the front and rear ends of the AGV, for respectively acquiring a first road surface image and a second road surface image during the driving of the AGV; A spatial observation unit, used to construct a spatial state equation during the driving of the AGV, and to calculate the position difference and driving deflection angle of the AGV when the first camera and the second camera shoot the same road position based on the spatial state equation; a correction unit, configured to correct the first road surface image and the second road surface image based on the position difference and the driving deflection angle; The leakage detection unit is used to compare the corrected first road surface image with the second road surface image to determine whether the hydraulic medium is leaking.

2. The hydraulic medium leakage detection system for automated terminal AGV according to claim 1, characterized in that: The spatial observation unit uses the following steps to construct the spatial state equation during AGV driving: Construct the discrete state equations of the AGV's lateral velocity, lateral displacement, longitudinal velocity, and longitudinal displacement: ;in, is the displacement in the X direction at the kth moment, is the velocity in the X direction at the kth moment, is the displacement in the Y direction at the kth moment, is the speed in the Y direction at the kth moment, T corresponds to the sampling time of the vehicle antenna and the vehicle speed sensor, and They are the accelerations in the X and Y directions provided by the AGV walking mechanism. and They are the operating noise interference caused by the AGV operation conditions; Establish the observation equation: ;in, The measured values ​​of the sensors are collected for information, , , , are the observation noise of the information acquisition sensor respectively; The discrete state equation and the observation equation are combined to obtain a set of spatial state equations.

3. The hydraulic medium leakage detection system for automated terminal AGV according to claim 2, characterized in that: The spatial observation unit measures the driving position and driving speed of the AGV based on the spatial state equation group; calculates the lateral position difference of the AGV when the first camera and the second camera shoot the same road position. , longitudinal position difference , and the driving deflection angle .

4. The hydraulic medium leakage detection system for automated terminal AGV according to claim 1, characterized in that: The leakage detection unit determines whether the hydraulic medium is leaking by the following steps: Using the HSV color model, extracting pixel points that match the color of the hydraulic oil from the first road surface image and the second road surface image; Calculating the difference between the pixel points extracted from the first road surface image and the pixel points extracted from the second road surface image; When the pixel point difference value is greater than a threshold value, it is determined that the hydraulic medium is leaking.

5. The hydraulic medium leakage detection system for automated terminal AGV according to claim 1, characterized in that: The system further comprises: The obstacle avoidance unit is used to prohibit the AGV from running and control other AGVs to avoid obstacles when the leakage detection unit determines that the hydraulic medium is leaking.

6. A method for detecting hydraulic medium leakage in an automated terminal AGV, characterized in that: include: Acquire a first road surface image and a second road surface image during the driving of the AGV by using a first camera and a second camera installed at the front and rear ends of the AGV; Constructing a spatial state equation during the driving of the AGV, and calculating the position difference and driving deflection angle of the AGV when the first camera and the second camera shoot the same road position based on the spatial state equation; correcting the first road surface image and the second road surface image based on the position difference and the travel deflection angle; The corrected first road surface image and the second road surface image are compared to determine whether the hydraulic medium is leaking.

7. The method for detecting hydraulic medium leakage for automated terminal AGV according to claim 6, characterized in that: The following steps are used to construct the spatial state equation during AGV driving: Construct the discrete state equations of the AGV's lateral velocity, lateral displacement, longitudinal velocity, and longitudinal displacement: ;in, is the displacement in the X direction at the kth moment, is the velocity in the X direction at the kth moment, is the displacement in the Y direction at the kth moment, is the speed in the Y direction at the kth moment, T corresponds to the sampling time of the vehicle antenna and the vehicle speed sensor, and They are the accelerations in the X and Y directions provided by the AGV walking mechanism. and They are the operating noise interference caused by the AGV operation conditions; Establish the observation equation: ;in, The measured values ​​of the sensors are collected for information, , , , are the observation noise of the sensor respectively; The discrete state equation and the observation equation are combined to obtain a set of spatial state equations.

8. The method for detecting hydraulic medium leakage for automated terminal AGV according to claim 7, characterized in that: Calculating the position difference and the driving deflection angle of the AGV when the first camera and the second camera shoot the same road position based on the spatial state equation includes: Measuring the driving position and driving speed of the AGV based on the spatial state equation group; Calculate the lateral position difference of the AGV when the first camera and the second camera shoot the same road position , longitudinal position difference , and the driving deflection angle .

9. The method for detecting hydraulic medium leakage for automated terminal AGV according to claim 6, characterized in that: Use the following steps to determine whether the hydraulic medium is leaking: Using the HSV color model, extracting pixel points that match the color of the hydraulic oil from the first road surface image and the second road surface image; Calculating the difference between the pixel points extracted from the first road surface image and the pixel points extracted from the second road surface image; When the pixel point difference value is greater than a threshold value, it is determined that the hydraulic medium is leaking.

10. The method for detecting hydraulic medium leakage for automated terminal AGV according to claim 9, characterized in that: The method further comprises: The hydraulic oil color threshold is set based on the color of the AGV driving field or environmental information.

Images