Battery positioning control method, device and equipment based on intelligent image recognition

Abstract

The present invention discloses a battery positioning control method, device and equipment based on intelligent image recognition, the method includes: obtaining a target detection framework that matches the input vehicle identification information, obtaining a battery frame image and constructing a virtual frame model, performing comparative calculations on the virtual frame model according to the target detection framework to obtain displacement deviation parameters and rotation deviation parameters, converting the rotation deviation parameters according to an angle conversion algorithm to obtain a target rotation angle, generating adjustment instructions corresponding to the position deviation parameters and the target rotation angle and sending them to a drive control device. The above method can obtain a target detection framework according to vehicle identification information, and perform comparative calculations on the virtual frame model corresponding to the battery frame image and the target detection model to achieve intelligent adjustment of the drive control device, so that the drive control device is adjusted to the corresponding grasping position to grasp the battery frame, and achieve efficient positioning and battery replacement operations for the battery.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a battery positioning control method, device and equipment based on intelligent image recognition. Background Art

[0002] With the rapid development of charging technology, the number of electric vehicles is increasing. When the battery in an electric vehicle needs to be repaired or replaced, the battery frame on which the battery is assembled needs to be removed from the vehicle. The prior art method is usually to manually operate a machine to align the battery frame. However, it is usually difficult to align the battery frame by manually operating mechanical equipment. If the mechanical equipment has a position deviation, it will collide with the battery frame and may cause damage to the battery, affecting the efficiency of battery replacement and disassembly. Therefore, the mechanical equipment used for battery replacement in the prior art method has the problem of being unable to quickly align the battery frame. Summary of the invention

[0003] The embodiments of the present invention provide a battery positioning control method, device and equipment based on intelligent image recognition, which aims to solve the problem that the mechanical equipment used for battery replacement in the prior art methods cannot be quickly aligned with the battery frame.

[0004] In a first aspect, an embodiment of the present invention provides a battery positioning control method based on intelligent image recognition, which is applied to a controller, wherein the controller establishes a network connection with an image acquisition device and a drive control device to realize data information transmission, and the method includes:

[0005] If the input vehicle identification information is received, a target detection frame matching the vehicle identification information is obtained from a preset detection frame library;

[0006] Acquire the battery frame image acquired by the image acquisition device and construct a corresponding virtual frame model according to a preset model construction rule;

[0007] Comparative calculation is performed on the virtual frame model according to the target detection framework to obtain corresponding displacement deviation parameters and rotation deviation parameters;

[0008] The rotation deviation parameter is converted according to a preset angle conversion algorithm to obtain a corresponding target rotation angle;

[0009] An adjustment instruction corresponding to the displacement deviation parameter and the target rotation angle is generated and sent to the drive control device to control the drive control device to adjust to a corresponding grasping position.

[0010] In a second aspect, an embodiment of the present invention further provides a battery positioning control device based on intelligent image recognition, wherein the device is configured in a controller, and the controller establishes a network connection with an image acquisition device and a drive control device to realize data information transmission. The device is used to execute the battery positioning control method based on intelligent image recognition as described in the first aspect above, and the device includes:

[0011] The target detection framework acquisition unit is used to acquire a target detection framework matching the vehicle identification information from a preset detection framework library if the input vehicle identification information is received;

[0012] A virtual frame model building unit, used to acquire the battery frame image acquired by the image acquisition device and build a corresponding virtual frame model according to a preset model building rule;

[0013] A deviation parameter acquisition unit, used to perform comparative calculation on the virtual frame model according to the target detection framework to obtain corresponding displacement deviation parameters and rotation deviation parameters;

[0014] A target rotation angle acquisition unit, used to convert the rotation deviation parameter according to a preset angle conversion algorithm to obtain a corresponding target rotation angle;

[0015] The adjustment instruction sending unit is used to generate an adjustment instruction corresponding to the displacement deviation parameter and the target rotation angle and send the adjustment instruction to the drive control device to control the drive control device to adjust to the corresponding grasping position.

[0016] In a third aspect, an embodiment of the present invention further provides a battery positioning control device based on intelligent image recognition, wherein the device includes a controller, an image acquisition device and a drive control device;

[0017] The driving control device comprises a machine platform, an X-axis moving assembly arranged on the machine platform, and a Y-axis moving assembly assembled on the X-axis moving assembly; the Y-axis moving assembly is rotationally connected to the Z-axis moving assembly via a slewing bearing, the Z-axis moving assembly is connected to the clamping claw slewing bracket via a wire rope, the clamping claw slewing bracket is provided with a latch, and the Z-axis moving assembly is provided with a fixing sleeve for fixing the latch;

[0018] The image acquisition device is fixedly arranged at the bottom of the clamping jaw rotating bracket, and the periphery of the image acquisition device is provided with an X-axis guide device and a Y-axis guide device connected to the clamping jaw rotating bracket;

[0019] The X-axis guide device and the Y-axis guide device are respectively provided with a drop-in-place detector; the R-axis rotating assembly provided on the Y-axis moving assembly is transmission-connected with the slewing bearing;

[0020] The controller is respectively connected to the image acquisition device and the PLC control module in the drive control device for communication; the PLC control module is respectively connected to the X-axis moving component, the Y-axis moving component, the Z-axis moving component, the R-axis rotating component and the drop-to-position detector for communication or electrical signal;

[0021] The controller includes a processor, a network interface, a memory and a communication bus, wherein the processor, the network interface and the memory communicate with each other via the communication bus;

[0022] Memory, used to store computer programs;

[0023] The processor is used to implement the steps of the battery positioning control method based on intelligent image recognition described in the first aspect when executing the program stored in the memory.

[0024] The embodiment of the present invention provides a battery positioning control method, device and equipment based on intelligent image recognition, the method includes: obtaining a target detection framework that matches the input vehicle identification information, obtaining a battery frame image and constructing a virtual frame model, performing comparative calculations on the virtual frame model according to the target detection framework to obtain displacement deviation parameters and rotation deviation parameters, converting the rotation deviation parameters according to an angle conversion algorithm to obtain a target rotation angle, generating adjustment instructions corresponding to the position deviation parameters and the target rotation angle and sending them to a drive control device. The above method can obtain a target detection framework according to vehicle identification information, and perform comparative calculations on the virtual frame model corresponding to the battery frame image and the target detection model to achieve intelligent adjustment of the drive control device, so that the drive control device is adjusted to the corresponding grasping position to grasp the battery frame, and achieve efficient positioning and battery replacement operations for the battery. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are 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 any creative work.

[0026] Figure 1 A method flow chart of a battery positioning control method based on intelligent image recognition provided by an embodiment of the present invention;

[0027] Figure 2 A schematic diagram of an application scenario of a battery positioning control method based on intelligent image recognition provided by an embodiment of the present invention;

[0028] Figure 3A schematic block diagram of a battery positioning control device based on intelligent image recognition provided by an embodiment of the present invention;

[0029] Figure 4 A schematic block diagram of a computer device provided for an embodiment of the present invention;

[0030] Figure 5 Another structural diagram of a drive control device provided by an embodiment of the present invention;

[0031] Figure 6 Another structural diagram of a drive control device provided by an embodiment of the present invention;

[0032] Figure 7 The following is a structural diagram of a drive control device provided by an embodiment of the present invention;

[0033] Figure 8 Another structural diagram of the drive control device provided by the embodiment of the present invention;

[0034] Fig. 9 Another structural diagram of the drive control device provided by the embodiment of the present invention;

[0035] Fig.10 Another structural diagram of the drive control device provided by the embodiment of the present invention;

[0036] Fig.11 Another structural diagram of the drive control device provided by the embodiment of the present invention;

[0037] Fig.12 Another structural diagram of the drive control device provided by the embodiment of the present invention;

[0038] Fig.13 Another structural diagram of the drive control device provided by the embodiment of the present invention;

[0039] Fig.14 Another structural diagram of the drive control device provided by the embodiment of the present invention;

[0040] Fig.15 A partial structural diagram of a drive control device provided by an embodiment of the present invention;

[0041] Fig.16 A schematic diagram of the application process of the drive control device provided by an embodiment of the present invention;

[0042] Fig.17 A schematic diagram of another application process of the drive control device provided in an embodiment of the present invention.

[0043] Figure numerals: 10, controller; 20, image acquisition device; 30, drive control device; 31, machine table; 32, X-axis moving assembly; 33, Y-axis moving assembly; 34, Z-axis moving assembly; 341, slewing bearing; 35, gripper slewing bracket; 36, X-axis guide device; 37, Y-axis guide device; 38, descent into position detector; 39, R-axis rotation assembly; 391, slewing motor; 392, turntable; 393, first connecting rod; 394, second connecting rod; 342, fixed sleeve. DETAILED DESCRIPTION

[0044] 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 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.

[0045] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0046] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0047] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0048] See also Figure 1 As shown in the figure, the embodiment of the present invention provides a battery positioning control method based on intelligent image recognition, which is applied to the controller 10 and executed by the application software installed in the controller 10. Specific application scenarios are as follows Figure 2As shown, the controller 10 establishes a network connection with the image acquisition device 20 and the drive control device 30 to realize data information transmission; wherein, the image acquisition device 20 is mounted on the drive control device 30, and the image acquisition device 20 is used to photograph the battery frame on which the battery pack is installed to obtain a battery frame image; the battery frame image is sent to the controller 10 for analysis, and the controller 10 sends a corresponding adjustment instruction to the drive control device 30 according to the analysis result, and the drive control device 30 adjusts to the corresponding grasping position according to the adjustment instruction, and the drive control device 30 is embedded in the battery frame at the exact position corresponding to the battery frame through the guide device provided thereon, thereby realizing accurate grasping of the battery frame. The controller 10 is a terminal device configured on the drive control device 30 for driving and controlling the drive control device 30, and the controller 10 can be an MCU chip or a control circuit with data processing and information receiving and sending functions. As shown in FIG. Figure 1 As shown, the method includes steps S110 to S150.

[0049] S110: If the input vehicle identification information is received, obtain a target detection frame that matches the vehicle identification information from a preset detection frame library.

[0050] If the input vehicle identification information is received, a target detection framework that matches the vehicle identification information is obtained from the preset detection framework library. The user can input the vehicle identification information into the controller. When the controller receives the vehicle identification information, it matches the vehicle configuration information through the pre-configured detection framework library. The detection framework library stores detection frameworks corresponding to various vehicle types. The detection frameworks stored in the detection framework library contain corresponding vehicle identifications. The battery frame sizes and shapes of different types of vehicles are different, so different detection frameworks need to be set for different types of vehicles. The vehicle identification information input by the user can be matched with the vehicle identifications contained in the corresponding detection frameworks in the detection framework library, so as to obtain a detection framework that matches the vehicle identification information as the target detection framework. Among them, the vehicle identification information can be a vehicle license plate, or a combination of a vehicle manufacturer and a vehicle model.

[0051] S120, acquiring the battery frame image acquired by the image acquisition device and constructing a corresponding virtual frame model according to a preset model construction rule.

[0052] The battery frame image acquired by the image acquisition device is obtained and a corresponding virtual frame model is constructed according to preset model construction rules. The controller sends an acquisition instruction to the image acquisition device, and the image acquisition device photographs the battery frame of the current vehicle according to the acquisition instruction, thereby obtaining battery frame information and sending it to the controller. The controller receives the battery frame image acquired by the image acquisition device, and then constructs a virtual frame model corresponding to the battery frame image according to the pre-configured model construction rules. The model construction rules are specific rules for constructing the virtual frame model, and the virtual frame model is a virtual model corresponding to the battery frame of the current vehicle generated based on three-dimensional modeling.

[0053] In a specific embodiment, step S120 includes sub-steps: extracting a corresponding frame contour image from the battery frame image according to the contour extraction algorithm in the model building rule; extracting corresponding frame point cloud data from the frame contour image according to the point cloud data extraction strategy in the model building rule; and performing three-dimensional modeling based on the frame point cloud data to construct a corresponding virtual frame model.

[0054] Specifically, the frame contour image can be extracted from the battery frame image according to the contour extraction algorithm in the model construction rule. The pixel contrast value between each pixel in the battery frame image and the surrounding pixels can be calculated according to the contour extraction algorithm. Each pixel corresponds to a pixel value (grayscale value or RGB pixel value). The difference between the pixel value and other adjacent pixels is calculated, and the average value is calculated to obtain the pixel contrast value. The pixel contrast value corresponding to the pixel and the pixel points in the outer circle can be calculated, and the pixel contrast value corresponding to the pixel and the pixel points in the outer circle and the outer two circles can also be calculated. The pixels contained in the battery frame image are sorted according to the calculated pixel contrast value, and the pixels with larger pixel contrast values ​​are sorted first, and the pixels with smaller pixel contrast values ​​are sorted last. According to the pre-set dissolution ratio, the front part of the pixels are intercepted from the sorted pixels and retained. Since the pixel contrast of the pixels at the edge of the frame in the battery frame image is larger, the pixels at the edge of the frame need to be retained, and the retained pixels constitute the frame contour image.

[0055] Furthermore, the corresponding frame point cloud data is extracted from the frame outline image according to the point cloud data extraction strategy, and the point cloud data extraction strategy includes the pixel extraction density of each area in the frame outline image, and some pixels are correspondingly extracted from the frame outline image as the frame point cloud data according to the pixel extraction density of different areas. For example, if the pixel extraction density of the pixels in a certain area is 0.25, then some pixels are extracted from the corresponding pixels in the frame outline image of the area at a ratio of 0.25 as the frame point cloud data corresponding to the area. The frame point cloud data corresponding to each area can be combined to obtain the frame point cloud data of the frame outline image.

[0056] Three-dimensional modeling is performed based on the extracted frame point cloud data to construct a virtual frame model. According to the position of each pixel point in the extracted frame point cloud data, each pixel point is placed in a three-dimensional space to achieve three-dimensional modeling and construct a virtual frame model. The virtual frame model is a non-solid model constructed inside the control.

[0057] In a specific embodiment, before step S120, the step further includes: sending a pre-stored homing control signal to the drive control device to control the drive control device to adjust to an initial position.

[0058] Furthermore, in order to improve the accuracy of positioning the battery, before acquiring the battery frame image through the image acquisition device, a pre-stored homing control signal can be sent to the drive control device, and the homing control signal includes the initial coordinate position of the device for frame scanning detection, such as the initial coordinate position is (X0, Y0, Z0, R0), where (X0, Y0, Z0) is the target coordinate value for three-dimensional movement of the gripper rotating bracket, and R0 is the target angle value for rotating the gripper rotating bracket. After receiving the homing control signal, the drive control device can drive the gripper rotating bracket to move to the initial position corresponding to the initial coordinate position based on the initial coordinate position contained in the homing control signal.

[0059] S130 , performing comparative calculation on the virtual frame model according to the target detection framework to obtain corresponding displacement deviation parameters and rotation deviation parameters.

[0060] The virtual frame model is compared and calculated according to the target detection framework to obtain corresponding displacement deviation parameters and rotation deviation parameters. Further, the target detection framework and the virtual frame model can be compared and calculated to obtain the difference between the target detection framework and the virtual detection framework, and the corresponding displacement deviation parameters and rotation deviation parameters are obtained based on the difference.

[0061] In a specific embodiment, step S130 includes sub-steps: obtaining a frame deflection angle from the virtual frame model and comparing it with a reference angle in the target detection frame to obtain a corresponding rotation deviation parameter; obtaining a frame center point coordinate from the virtual frame model and comparing it with a reference center point coordinate in the target detection frame to obtain a corresponding translation deviation parameter; obtaining a vertical distance parameter from the virtual frame model and combining it with the translation deviation parameter as the displacement deviation parameter.

[0062] Specifically, the frame deflection angle can be obtained from the virtual frame model and compared with the reference angle of the target detection frame. For example, the angle between the long sides on both sides and the horizontal direction can be obtained from the virtual frame model and the average value can be calculated as the corresponding long side deflection angle; the angle between the short sides on both ends and the horizontal direction can be obtained from the virtual frame model and the average value can be calculated as the corresponding short side deflection angle. The long side deflection angle and the short side deflection angle are averaged to obtain the frame deflection angle. Furthermore, the obtained long side deflection angle and short side deflection angle can be weighted according to the average length of the long side and the average length of the short side. The specific calculation formula is ΔR =(L×θ L +W×θ W ) / (L+W), where L is the average length of the long side, W is the average length of the short side, θ L is the long side deflection angle, θ W is the short side deflection angle; a more accurate frame deflection angle can be obtained through the above weighted calculation. The difference between the frame deflection handover and the reference angle of the target detection frame is calculated to obtain the rotation deviation parameter ΔR.

[0063] The coordinate positions of the four vertices in the virtual frame model can be obtained and cross-connected. The intersection point is the coordinate of the frame center point. The difference between the coordinate of the frame center point and the coordinate of the reference center point in the target detection frame is calculated to obtain the translation deviation parameters (ΔX, ΔY).

[0064] Furthermore, the vertical distance parameter can be obtained from the virtual frame model. The vertical distance parameter is to establish a plane on the upper surface of the virtual frame model, obtain the vertical distance between the plane and the seat point set in the image acquisition device, thereby obtaining the vertical distance, and then convert it to obtain the Z-axis height data of the device as the vertical distance parameter.

[0065] The translation deviation parameter and the vertical distance parameter can be calculated by the above method, and the displacement deviation parameter can be obtained by combining the translation deviation parameter and the vertical distance parameter.

[0066] S140: Convert the rotation deviation parameter according to a preset angle conversion algorithm to obtain a corresponding target rotation angle.

[0067] The rotation deviation parameter is converted according to a preset angle conversion algorithm to obtain a corresponding target rotation angle. Further, the rotation deviation parameter can be converted according to the angle conversion algorithm. Specifically, the mechanical structure of the R-axis rotation component can be modeled, that is, simplified as follows: Fig.16 As shown, it can be simplified into a connecting rod with known lengths of rods a, b, and c. Rod a rotates around point A, rod c rotates around point B, point D moves on a circle with point B as the center and rod c as the radius, and point C moves on a circle with point A as the origin and rod a as the radius. The above simplified model is placed in a rectangular coordinate system, with point A as the origin of the coordinate system. The coordinates of point B can be directly measured and obtained from the mechanical drawings, thereby converting the engineering problem into a mathematical equation for solution and verification. Among them, the r angle data can be converted and obtained through 3D detection, and the motor rotation angle t is obtained by applying the equation solution based on the r angle.

[0068] The specific solution process is as follows: using the trigonometric function relationship, first calculate the coordinates of point C; establish a coordinate system with point B, use trigonometric functions to calculate the coordinates of point D in the coordinate system, and then convert the coordinate system into a coordinate point in the coordinate system with point A as the origin; according to the distance formula between the two points, establish the equations of r and t as shown in formula (2):

[0069] (2);

[0070] Among them, a is Fig.16 The length of line segment a, b is the length of line segment b, c is the length of line segment c, B x and B y is the coordinate value of point B relative to point A (with A as the origin).

[0071] Using mathematical engineering software to solve for t, this equation will obtain two more complex solutions. Among them, solution 1 is t=-log((- 300614*exp(r*1i) + exp(r*2i)*(145083 - 50142i) + 411*((109725 / 139493 +exp(r*2i) - exp(r*1i)*(102904442 / 57331623 + 35564708i / 57331623) + 86132i / 139493)*(109725 / 139493 + exp(r*2i) - exp(r*1i)*(107599342 / 57331623 +37187308i / 57331623) + 86132i / 139493)*(109725 - 86132i))^(1 / 2) + (145083 +50142i)) / (70*(- 411 + exp(r*1i)*(353 - 122i))))*1i; Solution 2 is t= -log(-(300614*exp(r*1i) - exp(r*2i)*(145083 - 50142i) + 411*((109725 / 139493 + exp(r*2i) - exp(r*1i)*(102904442 / 57331623 + 35564708i / 57331623) + 86132i / 139493)*(109725 / 139493 + exp(r*2i) - exp(r*1i)*(107599342 / 57331623 + 37187308i / 57331623) +86132i / 139493)*(109725 - 86132i))^(1 / 2) - (145083 + 50142i)) / (70*(- 411 + exp(r*1i)*(353 - 122i))))*1i. Where i is an imaginary number.

[0072] Using 3D modeling tools, we build a geometric simulation model based on the constraint relationship between the connecting rod and each point, taking angle r as the driving data and angle t as the driven data. By inputting the angle r value, we can quickly get the angle value of t. The specific simulation model is as follows: Fig.17 The mapping relationship between the r and t values ​​obtained by the simulation model is used to verify the two solutions obtained in the above steps, and a suitable solution is selected as the corresponding target rotation angle.

[0073] S150, generating an adjustment instruction corresponding to the displacement deviation parameter and the target rotation angle and sending the adjustment instruction to the drive control device to control the drive control device to adjust to a corresponding grasping position.

[0074] Generate an adjustment instruction corresponding to the displacement deviation parameter and the target rotation angle and send it to the drive control device to control the drive control device to adjust to the corresponding grasping position. Further, an adjustment instruction corresponding to the displacement deviation parameter and the target rotation angle can be generated and sent to the drive control device. The drive control device then adjusts the gripper rotary bracket to the corresponding grasping position according to the received adjustment instruction.

[0075] In a specific embodiment, step S150 includes sub-steps: obtaining a displacement adjustment value corresponding to the displacement deviation parameter based on the initial position parameter in the homing control signal; obtaining an angle adjustment value corresponding to the target rotation angle based on the initial position parameter; generating a corresponding adjustment instruction based on the position adjustment value and the angle adjustment value and sending it to the drive control device.

[0076] Specifically, the initial position parameter in the control signal can be used as a reference to obtain a displacement adjustment value corresponding to the displacement deviation parameter, and the displacement deviation parameter is superimposed on the initial position parameter to obtain the corresponding displacement adjustment value; the displacement adjustment value is used to perform translation adjustment on the gripper swivel bracket in three-dimensional space (translation adjustment along the X-axis, Y-axis and Z-axis). Furthermore, based on the initial position parameter as a reference, the angle adjustment value corresponding to the target rotation angle is obtained, and the target rotation angle is superimposed on the initial position parameter to obtain the corresponding angle adjustment value; the angle adjustment value is used to rotate and adjust the angle of the gripper swivel bracket around the Z-axis. An adjustment instruction is generated according to the acquired position adjustment value and angle adjustment value and sent to the drive control device, and the generated adjustment instruction includes the position adjustment value and the angle adjustment value.

[0077] In the battery positioning control method based on intelligent image recognition disclosed in the above embodiment, the method includes: obtaining a target detection framework that matches the input vehicle identification information, obtaining a battery frame image and constructing a virtual frame model, performing comparative calculations on the virtual frame model according to the target detection framework to obtain displacement deviation parameters and rotation deviation parameters, converting the rotation deviation parameters according to an angle conversion algorithm to obtain a target rotation angle, generating adjustment instructions corresponding to the position deviation parameters and the target rotation angle and sending them to the drive control device. The above method can obtain the target detection framework according to the vehicle identification information, and perform comparative calculations on the virtual frame model corresponding to the battery frame image and the target detection model to achieve intelligent adjustment of the drive control device, so that the drive control device is adjusted to the corresponding grasping position to grasp the battery frame, and achieve efficient positioning and battery replacement operations for the battery.

[0078] The embodiment of the present invention also provides a battery positioning control device based on intelligent image recognition, which can be configured in a controller and is used to execute any embodiment of the aforementioned battery positioning control method based on intelligent image recognition. Figure 3 , Figure 3 A schematic block diagram of a battery positioning control device based on intelligent image recognition provided by an embodiment of the present invention.

[0079] like Figure 3 As shown, the battery positioning control device 100 based on intelligent image recognition includes a target detection framework acquisition unit 110, a virtual framework model construction unit 120, a deviation parameter acquisition unit 130, a target rotation angle acquisition unit 140 and an adjustment instruction sending unit 150.

[0080] The target detection framework acquisition unit 110 is used to acquire a target detection framework matching the vehicle identification information from a preset detection framework library upon receiving the input vehicle identification information.

[0081] The virtual frame model building unit 120 is used to obtain the battery frame image acquired by the image acquisition device and build a corresponding virtual frame model according to a preset model building rule.

[0082] In a specific embodiment, the virtual frame model construction unit 120 includes sub-units: a frame contour image acquisition unit, which is used to extract the corresponding frame contour image from the battery frame image according to the contour extraction algorithm in the model construction rule; a frame point cloud data acquisition unit, which is used to extract the corresponding frame point cloud data from the frame contour image according to the point cloud data extraction strategy in the model construction rule; and a model construction unit, which is used to perform three-dimensional modeling based on the frame point cloud data to construct a corresponding virtual frame model.

[0083] The deviation parameter acquisition unit 130 is used to perform comparative calculation on the virtual frame model according to the target detection framework to obtain corresponding displacement deviation parameters and rotation deviation parameters.

[0084] In a specific embodiment, the deviation parameter acquisition unit 130 includes sub-units: a rotation deviation parameter acquisition unit, which is used to obtain the frame deflection angle from the virtual frame model and compare and calculate with the reference angle in the target detection frame to obtain the corresponding rotation deviation parameter; a translation deviation parameter acquisition unit, which is used to obtain the frame center point coordinates from the virtual frame model and compare and calculate with the reference center point coordinates in the target detection frame to obtain the corresponding translation deviation parameter; a deviation parameter combination unit, which is used to obtain the vertical distance parameter from the virtual frame model and combine it with the translation deviation parameter into the displacement deviation parameter.

[0085] The target rotation angle acquisition unit 140 is used to convert the rotation deviation parameter according to a preset angle conversion algorithm to obtain a corresponding target rotation angle.

[0086] The adjustment instruction sending unit 150 is used to generate an adjustment instruction corresponding to the displacement deviation parameter and the target rotation angle and send the adjustment instruction to the drive control device to control the drive control device to adjust to the corresponding grasping position.

[0087] The battery positioning control device based on intelligent image recognition provided in the embodiment of the present invention applies the above-mentioned battery positioning control method based on intelligent image recognition, obtains a target detection framework that matches the input vehicle identification information, obtains a battery frame image and constructs a virtual frame model, compares and calculates the virtual frame model according to the target detection framework, obtains displacement deviation parameters and rotation deviation parameters, converts the rotation deviation parameters according to the angle conversion algorithm to obtain the target rotation angle, generates adjustment instructions corresponding to the position deviation parameters and the target rotation angle, and sends them to the drive control device. The above-mentioned method can obtain the target detection framework according to the vehicle identification information, and compares and calculates the virtual frame model corresponding to the battery frame image with the target detection model to realize intelligent adjustment of the drive control device, so that the drive control device is adjusted to the corresponding grasping position to grasp the battery frame, and realizes efficient positioning and battery replacement operations of the battery.

[0088] The embodiment of the present invention also provides a battery positioning control device based on intelligent image recognition, wherein the device includes a controller 10, an image acquisition device 20 and a drive control device 30; the drive control device 30 includes a machine platform 31 and an X-axis moving component 32 disposed on the machine platform 31, and a Y-axis moving component 33 assembled on the X-axis moving component 32; the Y-axis moving component 33 is rotationally connected to the Z-axis moving component 34 via a slewing bearing 341, and the Z-axis moving component 34 is connected to a clamping claw rotating bracket 35 via a wire rope, and a latch is provided on the clamping claw rotating bracket 35, and a fixing sleeve 342 for fixing the latch is provided on the Z-axis moving component 34. The assembly relationship between the X-axis moving component 32 and the Y-axis moving component 33 and the machine platform 31 is as follows: Figure 5 The assembly relationship between the Z-axis moving assembly 34, the slewing bearing 341 and the Y-axis moving assembly 33 is shown in FIG. Figure 6 As shown, the Z-axis moving assembly 34 can rotate relative to the Y-axis moving assembly 33 with the slewing bearing 341 as the axis. Fig.10 As shown, a latch is provided on the jaw rotating bracket 35, and a fixed sleeve 342 for fixing the latch is provided on the Z-axis moving component 34. When the jaw rotating bracket 35 is raised to the top, the latch is inserted into the fixed sleeve 342 for locking. This avoids the jaw rotating bracket 35 from shaking due to an unstable wire rope connection during X-axis translation, Y-axis translation and R-axis rotation, thereby improving the stability of the fixed connection of the jaw rotating bracket 35.

[0089] The Z-axis moving assembly 34 is connected to the clamping claw rotating bracket 35 through a steel wire rope, and the assembly relationship is as follows: Figure 7As shown, when the Z-axis moving assembly 34 rotates around the slewing bearing 341, the clamping claw slewing bracket 35 can be driven to rotate at the same time; the image acquisition device 20 is fixedly arranged at the bottom of the clamping claw slewing bracket 35, and the assembly relationship thereof is as shown in FIG. Figure 8 The image acquisition device 20 is provided with an X-axis guide device 36 and a Y-axis guide device 37 connected to the jaw rotating bracket 35, and the structure is set as Fig. 9 , Fig.10 and Fig.11 The X-axis guide device 36 and the Y-axis guide device 37 are respectively provided with a drop-in-place detector 38, and the structure is set as Fig.12 and Fig.13 The R-axis rotating assembly 39 provided on the Y-axis moving assembly 33 is connected to the slewing bearing 341 for transmission, and the structure is set as Fig.14 As shown; the controller 10 is respectively connected to the image acquisition device 20 and the PLC control module in the drive control device; the PLC control module is respectively connected to the X-axis moving component 32, the Y-axis moving component 33, the Z-axis moving component 34, the R-axis rotating component 39 and the drop-in-place detector 38 for communication or electrical signal connection, then the controller 10 sends a drive control signal to the PLC control module, and the PLC control module can drive and control each component accordingly. The X-axis guide device 36 and the Y-axis guide device 37 are a set of mechanical guide plates that can correct positioning deviations to ensure that the gripper swivel bracket 35 can be accurately clamped above the battery rectangular tube. The drop-in-place detector 38 can be used to detect whether the Z-axis direction has dropped into place, and is used to compensate for the Z-axis positioning deviation problem caused by the wire rope being pulled up and deformed after being stressed.

[0090] In a specific embodiment, the R-axis rotating assembly 39 includes a rotary motor 391, a turntable 392, a first connecting rod 393 and a second connecting rod 394; the turntable 392 is connected to the transmission shaft of the rotary motor 391, one end of the first connecting rod 393 is rotationally connected to the edge of the turntable 392, and the other end of the first connecting rod 393 is rotationally connected to one end of the second connecting rod 394; the other end of the second connecting rod 394 is rotationally connected to the edge of the rotary bearing 341. The specific structure is as follows: Fig.15 As shown, Fig.15 That is to construct Fig.16 Structural basis of the simulation model shown.

[0091] The computer program configured in the above controller can be Figure 4 If the controller runs on the computer device shown in the figure, the controller can be implemented as a computer device.

[0092] See also Figure 4 , Figure 4is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device may be a controller for executing a battery positioning control method based on intelligent image recognition to control a drive control device to achieve battery positioning control.

[0093] See also Figure 4 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a communication bus 501 , wherein the memory may include a storage medium 503 and an internal memory 504 .

[0094] The storage medium 503 can store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 can execute a battery positioning control method based on intelligent image recognition, wherein the storage medium 503 can be a volatile storage medium or a non-volatile storage medium.

[0095] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0096] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute the battery positioning control method based on intelligent image recognition.

[0097] The network interface 505 is used for network communication, such as providing data information transmission, etc. Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device 500 to which the solution of the present invention is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0098] The processor 502 is used to run the computer program 5032 stored in the memory to implement the corresponding functions in the above-mentioned battery positioning control method based on intelligent image recognition.

[0099] Those skilled in the art will understand that Figure 4 The embodiments of the computer device shown in the figure do not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such embodiments, the structure and function of the memory and the processor are the same as those of the embodiment of the present invention. Figure 4 The embodiments shown are consistent and will not be described again here.

[0100] It should be understood that in the embodiment of the present invention, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0101] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a volatile or non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps included in the battery positioning control method based on intelligent image recognition are implemented.

[0102] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the above-described equipment, devices and units can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. Those of ordinary skill in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0103] In the several embodiments provided by the present invention, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. Units with the same function may also be combined into one unit. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices or units, or may be an electrical, mechanical or other form of connection.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0105] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0106] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a computer-readable storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a magnetic disk or an optical disk.

[0107] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A battery positioning control method based on intelligent image recognition, characterized in that: The method is applied in a controller, wherein the controller establishes a network connection with an image acquisition device and a drive control device to realize data information transmission, the controller is communicated with a PLC control module in the drive control device, and the PLC control module is communicated or electrically connected with an X-axis moving component, a Y-axis moving component, a Z-axis moving component, an R-axis rotating component, and a drop-in-place detector, respectively. The method comprises: If the input vehicle identification information is received, a target detection frame matching the vehicle identification information is obtained from a preset detection frame library; Acquire the battery frame image acquired by the image acquisition device and construct a corresponding virtual frame model according to a preset model construction rule; Comparative calculation is performed on the virtual frame model according to the target detection framework to obtain corresponding displacement deviation parameters and rotation deviation parameters; The rotation deviation parameter is converted according to a preset angle conversion algorithm to obtain a corresponding target rotation angle; The angle conversion algorithm is a mathematical equation corresponding to the mechanical structure of the R-axis rotation component constructed using a trigonometric function relationship. The mathematical equation is: , a is the length of rod a in the R-axis rotation assembly, b is the length of rod b in the R-axis rotation assembly, c is the length of rod c in the R-axis rotation assembly, rod a rotates around point A, rod c rotates around point B, B x and B y is the coordinate value of point B relative to point A when A is the origin, r is the angle of rotation of rod a around point A, and t is the rotation angle of the motor; converting the rotation deviation parameter according to a preset angle conversion algorithm to obtain a corresponding target rotation angle includes: inputting the rotation deviation parameter into the angle conversion algorithm to solve the equation to obtain a corresponding solution; verifying the obtained solution and selecting one of the solutions as the corresponding target rotation angle; Generate an adjustment instruction corresponding to the displacement deviation parameter and the target rotation angle and send it to the drive control device to control the drive control device to adjust to the corresponding grasping position; the PLC control module in the drive control device drives the X-axis moving component, the Y-axis moving component and the Z-axis moving component according to the adjustment instruction to drive the gripper rotary bracket to move in translation, and the descending detector is used to detect whether the gripper rotary bracket has descended to the position in the Z-axis direction; the PLC control module in the drive control device drives the R-axis rotating component according to the adjustment instruction to drive the folder The claw swivel bracket rotates to adjust the grasping position.

2. The battery positioning control method based on intelligent image recognition according to claim 1 is characterized in that: The method of acquiring the battery frame image acquired by the image acquisition device and constructing a corresponding virtual frame model according to a preset model construction rule includes: Extracting a corresponding frame contour image from the battery frame image according to a contour extraction algorithm in the model building rule; Extracting corresponding frame point cloud data from the frame contour image according to the point cloud data extraction strategy in the model building rule; Three-dimensional modeling is performed based on the framework point cloud data to construct a corresponding virtual framework model.

3. The battery positioning control method based on intelligent image recognition according to claim 1 is characterized in that: The comparing and calculating the virtual frame model according to the target detection framework to obtain corresponding displacement deviation parameters and rotation deviation parameters includes: Obtaining a frame deflection angle from the virtual frame model and performing comparison calculation with a reference angle in the target detection frame to obtain a corresponding rotation deviation parameter; Obtaining the coordinates of the frame center point from the virtual frame model and comparing and calculating the coordinates of the reference center point in the target detection frame to obtain corresponding translation deviation parameters; A vertical distance parameter is obtained from the virtual frame model and combined with the translation deviation parameter to form the displacement deviation parameter.

4. The battery positioning control method based on intelligent image recognition according to any one of claims 1 to 3, characterized in that: Before acquiring the battery frame image acquired by the image acquisition device and constructing the corresponding virtual frame model, the method further includes: A pre-stored homing control signal is sent to the drive control device to control the drive control device to adjust to an initial position.

5. The battery positioning control method based on intelligent image recognition according to claim 4 is characterized in that: The step of generating an adjustment instruction corresponding to the displacement deviation parameter and the target rotation angle and sending the adjustment instruction to the drive control device comprises: Acquire a displacement adjustment value corresponding to the displacement deviation parameter based on the initial position parameter in the homing control signal; Acquire an angle adjustment value corresponding to the target rotation angle based on the initial position parameter; A corresponding adjustment instruction is generated according to the displacement adjustment value and the angle adjustment value and sent to the drive control device.

6. A battery positioning control device based on intelligent image recognition, characterized in that: The device is configured in a controller, and the controller establishes a network connection with an image acquisition device and a drive control device to realize data information transmission. The device is used to execute the battery positioning control method based on intelligent image recognition according to any one of claims 1 to 5, and the device includes: The target detection framework acquisition unit is used to acquire a target detection framework matching the vehicle identification information from a preset detection framework library if the input vehicle identification information is received; A virtual frame model building unit, used to acquire the battery frame image acquired by the image acquisition device and build a corresponding virtual frame model according to a preset model building rule; A deviation parameter acquisition unit, used to perform comparative calculation on the virtual frame model according to the target detection framework to obtain corresponding displacement deviation parameters and rotation deviation parameters; A target rotation angle acquisition unit, used to convert the rotation deviation parameter according to a preset angle conversion algorithm to obtain a corresponding target rotation angle; The adjustment instruction sending unit is used to generate an adjustment instruction corresponding to the displacement deviation parameter and the target rotation angle and send the adjustment instruction to the drive control device to control the drive control device to adjust to the corresponding grasping position.

7. The battery positioning control device based on intelligent image recognition according to claim 6, characterized in that: The virtual framework model building unit comprises: A frame contour image acquisition unit, used for extracting a corresponding frame contour image from the battery frame image according to a contour extraction algorithm in the model building rule; A framework point cloud data acquisition unit, used for extracting corresponding framework point cloud data from the framework contour image according to the point cloud data extraction strategy in the model building rule; The model building unit is used to perform three-dimensional modeling according to the framework point cloud data to construct a corresponding virtual framework model.

8. The battery positioning control device based on intelligent image recognition according to claim 6, characterized in that: The deviation parameter acquisition unit includes: A rotation deviation parameter acquisition unit, used to obtain a frame deflection angle from the virtual frame model and compare and calculate it with a reference angle in the target detection frame to obtain a corresponding rotation deviation parameter; A translation deviation parameter acquisition unit, used to obtain the frame center point coordinates from the virtual frame model and compare and calculate the reference center point coordinates in the target detection frame to obtain corresponding translation deviation parameters; The deviation parameter combination unit is used to obtain a vertical distance parameter from the virtual frame model and combine it with the translation deviation parameter to form the displacement deviation parameter.

9. A battery positioning control device based on intelligent image recognition, characterized in that: The device includes a controller, an image acquisition device and a drive control device; The driving control device comprises a machine platform, an X-axis moving assembly arranged on the machine platform, and a Y-axis moving assembly assembled on the X-axis moving assembly; the Y-axis moving assembly is rotationally connected to the Z-axis moving assembly via a slewing bearing, the Z-axis moving assembly is connected to the clamping claw slewing bracket via a wire rope, the clamping claw slewing bracket is provided with a latch, and the Z-axis moving assembly is provided with a fixing sleeve for fixing the latch; The image acquisition device is fixedly arranged at the bottom of the clamping jaw rotating bracket, and the periphery of the image acquisition device is provided with an X-axis guide device and a Y-axis guide device connected to the clamping jaw rotating bracket; The X-axis guide device and the Y-axis guide device are respectively provided with a drop-in-place detector; the R-axis rotating assembly provided on the Y-axis moving assembly is transmission-connected with the slewing bearing; The controller is respectively connected to the image acquisition device and the PLC control module in the drive control device for communication; the PLC control module is respectively connected to the X-axis moving component, the Y-axis moving component, the Z-axis moving component, the R-axis rotating component and the drop-to-position detector for communication or electrical signal; The controller includes a processor, a network interface, a memory and a communication bus, wherein the processor, the network interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the battery positioning control method based on intelligent image recognition described in any one of claims 1 to 5 when executing the program stored in the memory.

10. The battery positioning control device based on intelligent image recognition according to claim 9, characterized in that: The R-axis rotating assembly includes a rotary motor, a turntable, a first connecting rod and a second connecting rod; The turntable is connected to the transmission shaft of the rotary motor, one end of the first connecting rod is rotationally connected to the edge of the turntable, the other end of the first connecting rod is rotationally connected to one end of the second connecting rod; the other end of the second connecting rod is rotationally connected to the edge of the slewing bearing.

Images