Adaptive control system, control device and method based on target detection

Abstract

The invention relates to the technical field of adaptive control, and discloses an adaptive control system, control equipment and method based on target detection, the adaptive control equipment is controlled through an execution subsystem, an object is detected through a detection subsystem, and the execution subsystem comprises a conveying module, a folding module and a conveying module. The conveying assembly is controlled by the conveying module to receive objects and convey the objects to the detection assembly, the folding assembly is controlled by the folding module to fold the objects to form finished products, and the conveying assembly is controlled by the conveying module to convey the folded finished products. The detection subsystem comprises a target detection module, whether an object located in the object detection cavity is abnormal or not is detected through the target detection module, the abnormal type is judged, and judgment of the abnormal type comprises the steps that an edge frame of the object is determined through an edge function and compared with a standard frame, and the abnormal type of the object is judged according to the continuity of the edge frame; the quality of the object meets the standard, the detection precision is improved, and the rejection rate is reduced.

Description

Technical Field

[0001] The present invention relates to the field of adaptive control technology, and in particular to an adaptive control system, control equipment and method based on target detection. Background Art

[0002] With the development of target detection technology, it is possible to efficiently identify and locate target objects in images, providing basic data for adaptive control systems. In the process of intelligent manufacturing, the operation of machines can be controlled through target detection, the flexibility and automation level of the production line can be improved, and it can adapt to different environments and working conditions, improve the adaptability and intelligence level of adaptive control systems, reduce human intervention, and improve production efficiency and safety. The adaptive control system for target objects here can be applied to fork machines to adaptively control foldable forks. However, most of them have not solved how to control the transportation of objects, detect whether the objects are abnormal and determine the type of abnormality, so as to form a mark, and control the folding and transportation of objects according to the mark. Packaging and classification processes.

[0003] For example, the patent application with publication number CN118068807A discloses a multi-objective fault detection method for aircraft engine actuators, which combines an adaptive event triggering mechanism with a fault detection observer and takes into account the network transmission delay effect, thereby achieving a balance between saving network bandwidth resources and ensuring system fault detection performance; then the design criteria of the multi-objective fault detection observer are given to ensure the robustness of the residual signal to external disturbances and the sensitivity to fault signals; finally, an aircraft engine control system model is used to verify the effectiveness of the proposed multi-objective fault detection method based on the adaptive event triggering mechanism.

[0004] For example, the Chinese patent application with the authorization announcement number CN108919373B discloses a target detection control device and its detection control method, device and storage medium. When receiving a target entry or exit signal, a temperature image data sampling signal is output, wherein the temperature image data sampling signal is used to control the second infrared sensor to collect temperature image data of a preset detection area; the temperature image data is received, and the target detection is performed according to the temperature image data and the target detection condition to obtain the detection result and output it. After the first infrared sensor determines that a target has entered or left, the second infrared sensor is triggered to collect temperature image data of the preset detection area, and the temperature image data and the target detection condition are used to determine whether there is a target in the preset detection area. Only after the first infrared sensor determines that a target has entered or left, the second infrared sensor is triggered to collect temperature image data of the preset detection area for detection, which can quickly determine whether there is a target in the preset detection area, thereby improving the detection efficiency.

[0005] The above patents have the problem raised by the background technology: the above two patents do not solve the problem of how to control the conveyance of objects, detect whether the objects are abnormal and determine the type of abnormality to form a mark, and control the folding and conveying of objects according to the mark. To solve this problem, the present invention proposes an adaptive control system, control device and method based on target detection. Summary of the invention

[0006] In view of the above problems existing in the existing adaptive control system, control device and method based on target detection, the present invention is proposed.

[0007] Therefore, the object of the present invention is to provide an adaptive control system, control device and method based on target detection.

[0008] In order to solve the above technical problems, the present invention provides an adaptive control system based on target detection: applied to an adaptive control device based on target detection, the adaptive control device comprises a conveying assembly, a detecting assembly and a folding assembly, the conveying assembly is used to receive an object formed by an injection molding machine and convey it to a detection object hole in the detecting assembly, the detecting assembly is used to detect the object and convey the detected object to the folding assembly, and the folding assembly is used to fold the object to form a finished product;

[0009] The adaptive control system comprises an execution subsystem and a detection subsystem, wherein the execution subsystem is used to control the adaptive control device, and the detection subsystem is used to detect objects;

[0010] The execution subsystem includes a conveying module and a folding module;

[0011] The conveying module is used to control the conveying assembly to receive the object and convey it to the detection assembly, and the folding module is used to control the folding assembly to fold the object into a finished product;

[0012] The detection subsystem includes a target detection module, which is used to detect whether an object located in a detection object hole has an abnormality and determine the type of abnormality. The determination of the abnormality type includes using an edge function to determine an edge border of the object and comparing it with a standard border to determine the abnormality type of the object based on the continuity of the edge border.

[0013] As a preferred solution of the adaptive control system based on target detection described in the present invention, the specific steps of detecting whether an object located in the detection object hole is abnormal include:

[0014] Acquire the image of the object in the detection object hole in real time to obtain the object image;

[0015] Configure a standard object image and calculate the difference between the object image and the standard object image;

[0016] Configure a difference threshold, compare the difference between the object image and the standard object image with the difference threshold, determine whether the object image has an abnormality, obtain the abnormal image and perform image analysis on the abnormal image;

[0017] Identify the abnormal type of the object, mark the abnormal object, form a sequence list, and generate a folding signal and transmit it to the folding assembly.

[0018] As a preferred solution of the adaptive control system based on target detection described in the present invention, the calculation formula of the difference between the object image and the standard object image is as follows:

[0019]

[0020] Where dis represents the difference between the object image and the standard object image, p represents the width of the target image, q represents the height of the target image, I1(a,b) represents the pixel value of the object image at position (a,b), I2(a,b) represents the pixel value of the standard object image at position (a,b), a represents the horizontal coordinate, and b represents the vertical coordinate;

[0021] The logic for determining whether an object image has an abnormality includes:

[0022] If the difference between the object image and the standard object image is less than or equal to the difference threshold, it means that there is no abnormality in the object image;

[0023] If the difference between the object image and the standard object image is greater than the difference threshold, it means that there is an abnormality in the object image.

[0024] As a preferred solution of the adaptive control system based on target detection described in the present invention, wherein: the object includes a force-bearing part and a hand-held part, and the specific steps of identifying the abnormal type of the object include:

[0025] An edge function is configured, and an edge frame used to characterize the edge of an object in the abnormal image is extracted based on the edge function, and the edge frame is compared with the configured standard frame to determine the abnormal type of the object;

[0026] If the edge frame is a continuous frame, it is further determined whether there is a fault in the edge frame. If there is a fault, the fault position is identified. If the fault position is in the force-bearing part, the abnormality type of the object is determined to be object fracture; if the fault position is in the hand-held part, the abnormality type of the object is determined to be surface abnormality.

[0027] If the edge frame is a discontinuous frame, the abnormal type of the object is determined to be a surface abnormality.

[0028] As a preferred solution of the adaptive control system based on target detection described in the present invention, it is judged whether the object can be aligned with the detection object hole in the detection assembly during transmission by the conveying assembly, and the alignment judgment logic includes:

[0029] Acquire a process of conveying the received object along the conveying assembly to the detection object hole in the detection assembly to obtain a conveying image;

[0030] Project the conveyed image onto a plane, identify objects and detect the edges of object holes;

[0031] Points are taken symmetrically along the edges of the object and the detection object hole, and the plane coordinates of the object edge points and the detection object hole edge points are obtained respectively;

[0032] Calculate the average offset between the edge point of the object and the edge point of the hole of the detected object, and determine the offset direction between the object and the hole of the detected object according to the positive and negative values ​​of the average offset between the edge point of the object and the hole of the detected object;

[0033] Configure the offset threshold, compare the average offset of the edge point of the object and the edge point of the detection object hole with the offset threshold to determine whether the object and the detection object hole are offset, and adjust the installation position of the conveying assembly according to the offset direction and the average offset.

[0034] As a preferred solution of the adaptive control system based on target detection described in the present invention, the logic for determining whether the object and the detection object hole are offset includes:

[0035] If the average offset between the edge point of the object and the edge point of the detected object hole is less than or equal to the offset threshold, it is considered that there is no offset between the object and the detected object hole;

[0036] If the average offset between the edge points of the object and the edge points of the detected object holes is greater than the offset threshold, it is considered that there is an offset between the object and the detected object holes.

[0037] An adaptive control device based on target detection includes: a body, a conveying assembly, a detection assembly and a folding assembly arranged on the body;

[0038] The conveying assembly is used to receive objects from the output end of the injection molding machine and convey them. The detection assembly is used to receive objects conveyed by the conveying assembly. A detection object hole is provided on the detection assembly. The object is placed in the detection object hole and detected. When the detection is completed, the detected object is conveyed to the folding assembly. The folding assembly is used to fold the object and form a finished product.

[0039] As a preferred solution of the adaptive control device based on target detection described in the present invention, the conveying assembly includes a support column and a supporting truss, the support column is provided with a first power source, the supporting truss is connected to the first power source, and a rotating motor is also provided at the connection between the supporting truss and the first power source, the rotating motor is used to control the rotation of the supporting truss, and the supporting truss is provided with a supporting suction cup for adsorbing objects.

[0040] As a preferred solution of the adaptive control device based on target detection described in the present invention, wherein: the detection assembly includes a second power source, an adsorption truss and a detection carrier, a support truss is provided on the machine body, a third power source is provided on the support truss, the third power source is connected to the second power source via a sliding seat, the second power source is provided on the sliding seat, the adsorption truss is slidably connected to the second power source, the second power source is used to control the adsorption truss to move toward or away from the detection carrier, the detection carrier is provided on the machine body, and a detection object hole is provided in the detection carrier, the adsorption truss is provided with an adsorption suction cup for adsorbing objects, and the adsorption truss is also provided with a detection module, and the detection module is used to perform visual detection on the object in the detection object hole;

[0041] The folding assembly includes a fourth power source, a clamping truss and a folding carrier, the fourth power source is connected to the third power source via the sliding seat, the fourth power source is arranged on the sliding seat, the clamping truss is slidably connected to the fourth power source, the folding carrier is arranged on the body, and a folding object hole is arranged on the folding carrier, the clamping truss is provided with a clamp for clamping an object, and the folding carrier is also provided with a pushing module, the pushing module is used to fold the object in the folding object hole and form a finished product, and the pushing module is provided with a cylinder for pushing the object in the folding object hole to fold.

[0042] An adaptive control method based on target detection includes: obtaining an electrical signal generated when an injection molding machine discharges materials, a conveying assembly receiving an object of the injection molding machine based on the electrical signal generated when the injection molding machine discharges materials and conveying the object to a detection assembly;

[0043] After the detection is completed, a folding signal is generated. Based on the folding signal, the detection assembly absorbs the object and moves it to the folding assembly, and the folding assembly folds the object to form a finished product.

[0044] Beneficial effects of the present invention: The present invention controls the adaptive control device through the execution subsystem, and detects the object through the detection subsystem, wherein the execution subsystem includes a conveying module, a folding module and a transmission module, and controls the conveying assembly through the conveying module to receive the object and transmit it to the detection assembly, thereby reducing the time and error rate of manual operation, and controls the folding assembly through the folding module to fold the object into a finished product, thereby improving the processing quality, and controls the transmission assembly through the transmission module to transmit the folded finished product, thereby shortening the production cycle; the detection subsystem includes a target detection module, and detects whether the object located in the detection object hole has an abnormality through the target detection module and determines the type of abnormality, and the determination of the abnormality type includes using an edge function to determine the edge frame of the object and comparing it with the standard frame, so as to determine the abnormality type of the object according to the continuity of the edge frame, thereby ensuring that the quality of the object meets the standard, and improving the detection accuracy and reducing the scrap rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0046] Figure 1 A system structure diagram of an adaptive control system based on target detection according to the present invention;

[0047] Figure 2 This is a logic flow chart of alignment judgment of an adaptive control system based on target detection according to the present invention;

[0048] Figure 3 A method flow chart of an adaptive control method based on target detection according to the present invention;

[0049] Figure 4 This is an overall structural diagram of an adaptive control device based on target detection according to the present invention;

[0050] Figure 5 A structural diagram of a conveying assembly of an adaptive control device based on target detection according to the present invention;

[0051] Figure 6 This is a structural diagram of a detection assembly of an adaptive control device based on target detection according to the present invention;

[0052] Figure 7 This is a structural diagram of a detection module of an adaptive control device based on target detection according to the present invention;

[0053] Figure 8 A structural diagram of a folding assembly of an adaptive control device based on target detection according to the present invention;

[0054] Fig. 9 For the present invention Figure 8 A magnified view of the structure at center;

[0055] Fig.10 This is a structural diagram of a transmission assembly of an adaptive control device based on target detection according to the present invention.

[0056] Reference numerals:

[0057] 1. Conveying assembly; 2. Detection assembly; 3. Folding assembly; 4. Transmission assembly; 5. Machine body; 11. Supporting pillar; 111. First power source; 12. Supporting truss; 121. Supporting suction cup; 13. Rotating motor; 21. Second power source; 22. Adsorption truss; 221. Adsorption suction cup; 222. Detection module; 2221. Top camera; 2222. Side camera; 23. Detection carrier; 231. Detection object hole; 31. Fourth power source; 32. Clamping truss; 321. Clamp; 33. Folding carrier; 331. Folding object hole; 332. Pushing module; 3321. Cylinder; 41. Fifth power source; 42. Transmission carrier; 421. Transmission member; 43. Transmission motor; 51. Supporting truss; 511. Third power source; 512. Sliding seat. DETAILED DESCRIPTION

[0058] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0060] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0061] Example 1

[0062] In this embodiment, a system structure diagram of an adaptive control system based on target detection is provided, such as Figure 1 As shown, an adaptive control system based on target detection is applied to an adaptive control device based on target detection.

[0063] The adaptive control device includes a conveying assembly, a detection assembly, a folding assembly and a transmission assembly. The conveying assembly is used to receive objects formed by an injection molding machine and convey them to a detection object hole in the detection assembly. The detection assembly is used to detect objects and convey the detected objects to the folding assembly. The folding assembly is used to fold objects and convey them to the conveying assembly. The conveying assembly is used to convey the folded objects and package them.

[0064] The adaptive control system includes an execution subsystem and a detection subsystem. The execution subsystem is used to control the adaptive control device, and the detection subsystem is used to detect objects.

[0065] The execution subsystem includes a conveying module, a folding module and a transmission module.

[0066] The conveying module is used to control the conveying assembly to receive the object and convey it to the detection assembly, the folding module is used to control the folding assembly to fold the object to form a finished product, and the transmission module is used to control the transmission assembly to convey the folded finished product.

[0067] The conveying module receives the object from the injection molding machine and conveys it to the detection assembly according to the electrical signal generated when the injection molding machine discharges the material. It is crucial for the object to be aligned with the detection object hole in the detection assembly during transmission through the conveying assembly. The alignment judgment logic is as follows: Figure 2 As shown, specifically including:

[0068] The process of conveying the received object along the conveying assembly to the detection object hole in the detection assembly is obtained by the camera from above to obtain a conveying image, which is projected onto a plane, and the edges of the object and the detection object hole are identified by an edge detection algorithm. Points are symmetrically taken along the edges of the object and the detection object hole to obtain the plane coordinates of the object edge points and the detection object hole edge points respectively, and the average offset of the object edge points and the detection object hole edge points is calculated. The offset direction of the object and the detection object hole is determined according to the positive and negative values ​​of the average offset of the object edge points and the detection object hole edge points, and an offset threshold is configured. The average offset of the object edge points and the detection object hole edge points is compared with the offset threshold to determine whether the object and the detection object hole are offset, and the installation position of the conveying assembly is adjusted according to the offset direction and the average offset to ensure that the object can be aligned with the detection object hole in the detection assembly during the conveying process, and after adjusting the installation position of the conveying assembly, the camera is used to shoot again to verify whether the object and the detection object hole are offset. If there is still deflection, the above process is repeated until a satisfactory alignment accuracy is achieved.

[0069] The calculation formula for the average offset between the edge points of the object and the edge points of the detected object holes is as follows:

[0070]

[0071] In the formula, represents the average offset between the edge points of the object and the edge points of the detected object holes, n represents the total number of points, s i represents the plane coordinates of the edge point of the i-th object, w i Represents the plane coordinates of the edge point of the i-th detected object hole.

[0072] It should be noted that: |s i -w i | refers to the distance between the edge point of the i-th object and the edge point of the i-th detected object hole, which is usually calculated using the Euclidean distance formula.

[0073] The logic for determining whether the object and the detection object hole are offset includes:

[0074] If the average offset between the edge point of the object and the edge point of the detected object hole is less than or equal to the offset threshold, it is considered that there is no offset between the object and the detected object hole;

[0075] If the average offset between the edge points of the object and the edge points of the detected object holes is greater than the offset threshold, it is considered that there is an offset between the object and the detected object holes.

[0076] After receiving the folding signal, the folding module controls the folding assembly to fold the object to form a finished product, and generates a conveying signal to convey the folded finished product to the conveying assembly.

[0077] After receiving the transmission signal, the transmission module identifies the sequence list, records the batches and quantities of all abnormal objects in the sequence list, and forms numbered labels for the abnormal objects in the corresponding batches and corresponding quantity positions, so as to facilitate the removal of the corresponding abnormal objects during subsequent packaging and replenish normal objects from other production lines.

[0078] The detection subsystem includes a target detection module, which is used to detect whether an object located in the detection object hole is abnormal and determine the type of abnormality.

[0079] When there is no offset between the object and the detection object hole, the object received at the output end of the injection molding machine is conveyed to the detection object hole in the detection assembly through the conveying assembly according to the determined position of the conveying assembly, and the image of the object in the detection object hole is acquired in real time to obtain the object image, configure the standard object image, calculate the difference between the object image and the standard object image, configure the difference threshold, compare the difference between the object image and the standard object image with the difference threshold, determine whether there is an abnormality in the object image, obtain the abnormal image and perform image analysis on the abnormal image, identify the abnormal type of the object, mark the object with the abnormality, form a sequence list, generate a folding signal, and convey it to the folding assembly.

[0080] The calculation formula of the difference between the object image and the standard object image is as follows:

[0081]

[0082] Where dis represents the difference between the object image and the standard object image, p represents the width of the target image, q represents the height of the target image, I1(a,b) represents the pixel value of the object image at position (a,b), I2(a,b) represents the pixel value of the standard object image at position (a,b), a represents the horizontal coordinate, and b represents the vertical coordinate.

[0083] It needs to be explained that: in actual applications, the width and height of the object image are inconsistent with the standard object image. Before calculating the difference between the object image and the standard object image, the object image and the standard object image are scaled to the size of the target image (usually using the bilinear interpolation method). After the scaling process, the width and height of the object image and the standard object image are consistent and have the same size; the width p of the target image refers to the horizontal number of pixels of the target image, and the height q of the target image refers to the vertical number of pixels of the target image. Usually, the width and height of the target image are both in pixels and are integers (usually greater than 1 pixel). If the width and height of the object image and the standard object image become non-integer after scaling, then before performing the summation operation, the non-integer width and height need to be rounded.

[0084] The logic for determining whether an object image has an abnormality includes:

[0085] If the difference between the object image and the standard object image is less than or equal to the difference threshold, it means that there is no abnormality in the object image;

[0086] If the difference between the object image and the standard object image is greater than the difference threshold, it means that there is an abnormality in the object image.

[0087] The object includes a force-bearing part and a hand-held part. The specific steps of identifying the abnormal type of the object include:

[0088] An edge function is configured, and an edge frame used to characterize the edge of an object in the abnormal image is extracted based on the edge function, and the edge frame is compared with the configured standard frame to determine the abnormal type of the object;

[0089] If the edge frame is a continuous frame, it is further determined whether there is a fault in the edge frame. If there is a fault, the fault position is identified. If the fault position is in the force-bearing part, the abnormality type of the object is determined to be object fracture; if the fault position is in the hand-held part, the abnormality type of the object is determined to be surface abnormality.

[0090] If the edge frame is a discontinuous frame, the abnormal type of the object is determined to be a surface abnormality.

[0091] When the abnormality type of the object is determined to be a surface abnormality, the specific abnormality type of the object is further determined, and a difference image is obtained by subtracting the abnormal image from the standard object image, and the position of the difference image is extracted. If the position of the difference image is within the standard frame, the specific abnormality type of the object is determined to be an object depression;

[0092] If the position of the difference image is outside the standard frame, the specific abnormal type of the object is determined to be a burr or a protrusion.

[0093] The edge border used to characterize the edge of the object in the abnormal image is extracted based on the edge function. The expression of the edge function is as follows:

[0094]

[0095] Where G(x, y, σ) represents the smoothing process of abnormal images, x and y represent the positions in the image coordinate system, σ represents the standard deviation, which is used to affect the smoothing degree of Gaussian filtering. When σ is larger, the image is more blurred, and when σ is smaller, the image is clearer and the smoothing effect is weaker. π represents pi, and e represents a mathematical constant, which is used to calculate the value of the edge function.

[0096] Example 2

[0097] In this embodiment, an overall structure diagram of an adaptive control device based on target detection is provided, such as Figure 4 As shown, an adaptive control device based on target detection includes a conveying assembly 1, a detection assembly 2, a folding assembly 3 and a transmission assembly 4.

[0098] The object in the embodiments refers to a foldable fork.

[0099] The adaptive control device based on target detection is used to detect and fold the foldable fork after injection molding in the injection molding machine, such as Figure 4 As shown, the adaptive control device includes a body 5, a conveying assembly 1, a detection assembly 2, a folding assembly 3 and a transmission assembly 4 arranged on the body 5, the conveying assembly 1 is used to receive and convey the foldable fork from the output end of the injection molding machine, the detection assembly 2 is used to receive the foldable fork conveyed by the conveying assembly 1, the detection assembly 2 is provided with a detection object hole 231, the foldable fork is placed in the detection object hole 231 and is detected, and when the detection is completed, the detected foldable fork is conveyed to the folding assembly 3, the folding assembly 3 is used to fold the foldable fork and form a finished product, and the transmission assembly 4 is used to convey the finished product folded by the folding assembly 3 to the next processing step, where the next processing step refers to the classification and packaging of the finished products.

[0100] like Figure 5As shown, the conveying assembly 1 includes a support column 11 and a supporting truss 12. The support column 11 is provided with a first power source 111, and the supporting truss 12 is connected to the first power source 111, so that the first power source 111 drives the supporting truss 12 to reciprocate along the length direction of the support column 11, and the supporting truss 12 is provided with a supporting suction cup 121 for adsorbing the foldable fork. The connection between the supporting truss 12 and the first power source 111 is also provided with a rotating motor 13, and the rotating motor 13 is used to control the rotation of the supporting truss 12 so that when receiving the foldable fork, the supporting truss 12 can be rotated. When folding the fork, the supporting truss 12 is controlled to rotate to the horizontal initial position, and the foldable fork is sucked by the supporting suction cup 121. When transporting the foldable fork, the rotating motor 13 rotates to drive the supporting truss 12 to rotate 180°. At the same time, the first power source 111 drives the supporting truss 12 to move along the length direction of the pillar 11 to the detection assembly 2, so that the foldable fork is aligned with the detection object hole 231 of the detection assembly 2, so that when the supporting suction cup 121 releases the suction, the foldable fork is placed in the detection object hole 231.

[0101] like Figure 6 As shown, the detection assembly 2 includes a second power source 21, an adsorption truss 22 and a detection carrier 23, a supporting truss 51 is arranged on the body 5, a third power source 511 is arranged on the supporting truss 51, the third power source 511 is connected to the second power source 21 via a sliding seat 512, the second power source 21 is arranged on the sliding seat 512, the adsorption truss 22 is slidably connected to the second power source 21, the detection carrier 23 is arranged on the body 5, and a detection object hole 231 is provided in the detection carrier 23, and an adsorption suction cup 221 for adsorbing a foldable fork is arranged on the adsorption truss 22. When the supporting truss 12 moves along the pillar 11 and places the foldable fork, the third power source 511 is used to drive the adsorption truss 22 and the detection carrier 23 to be dislocated so that the foldable fork can be placed in the detection object hole 231. After the foldable fork is placed, the supporting truss 12 moves back to the original position along the pillar 11.

[0102] like Figure 7 As shown, a detection module 222 is also provided on the adsorption truss 22. The detection module 222 is used to perform visual detection on the foldable fork in the detection object hole 231. When the foldable fork is placed in the detection object hole 231, the third power source 511 drives the adsorption truss 22 to move to a position opposite to the detection carrier 23. During the movement of the adsorption truss 22, the detection module 222 detects the foldable forks in the detection object hole 231 in turn, so that when the adsorption truss 22 is opposite to the detection carrier 23, the visual detection of all the foldable forks in the detection object hole 231 is completed. A top camera 2221 and a side camera 2222 are provided on the detection module 222, which are used to perform visual detection on the foldable fork in the detection object hole 231 and determine the position and abnormal state of the foldable fork.

[0103] The second power source 21 is used to control the adsorption truss 22 to move toward or away from the detection carrier 23, so that when it moves toward the detection carrier 23 and makes the adsorption suction cup 221 contact with the foldable fork, the foldable fork can be adsorbed by the adsorption suction cup 221, and the foldable fork is sucked out of the detection object hole 231 under the drive of the second power source 21, and the foldable fork can be driven to move along the direction of the supporting truss 51 under the action of the third power source 511.

[0104] like Figure 8 As shown, the folding assembly 3 includes a fourth power source 31, a clamping truss 32 and a folding carrier 33. The fourth power source 31 is connected to the third power source 511 via a sliding seat 512. The fourth power source 31 is arranged on the sliding seat 512. The clamping truss 32 is slidably connected to the fourth power source 31. The folding carrier 33 is arranged on the body 5, and a folding object hole 331 is arranged on the folding carrier 33. A clamp 321 for clamping a foldable fork is arranged on the clamping truss 32. When the adsorption truss 22 is driven by the third power source 511 to move along the supporting truss 51 and place the foldable fork, the third power source 511 is used to drive the clamping truss 32 and the folding carrier 33 to be misaligned so that the foldable fork can be placed in the folding object hole 331. After the foldable fork is placed, the adsorption truss 22 moves back along the supporting truss 51.

[0105] The folding carrier 33 is also provided with a pushing module 332, which is used to fold the foldable fork in the folding object hole 331 to form a finished product. The pushing module 332 is provided with a cylinder 3321 for pushing the foldable fork in the folding object hole 331 to fold. When the foldable fork is placed in the folding object hole 331, the third power source 511 drives the clamping truss 32 to move to a position relative to the folding carrier 33. During the movement of the clamping truss 32, the cylinder 3321 pushes the foldable fork in the folding object hole 331 to fold and form a finished product (such as Fig. 9 As shown), when the clamping truss 32 is opposite to the folding carrier 33, the folding of all the foldable forks in the folding object cavity 331 is completed and a finished product is formed.

[0106] The fourth power source 31 is used to control the clamping truss 32 to move toward or away from the folding carrier 33, so that when moving toward the folding carrier 33 and making the clamp 321 contact with the finished part, the foldable fork can be clamped by the clamp 321, and the folded finished part is clamped out of the folding object hole 331 under the drive of the fourth power source 31, and the folded finished part is driven to move along the direction of the supporting truss 51 and placed on the conveying assembly 4 under the action of the third power source 511.

[0107] like Fig.10As shown, the conveying assembly 4 includes a fifth power source 41 and a conveying carrier 42, a conveying member 421 is arranged on the conveying carrier 42, and the conveying member 421 is connected to the fifth power source 41 so that the fifth power source 41 drives the conveying member 421 to reciprocate along the length direction of the conveying carrier 42, and a conveying motor 43 is also arranged at the connection between the conveying member 421 and the fifth power source 41, and the conveying motor 43 is used to control the conveying of the conveying member 421, so that after receiving the folded finished parts, the conveying motor 43 drives the conveying member 421 to convey the folded finished parts along the length direction of the conveying carrier 42 to the next processing step, including completing the classification and packaging of the finished parts according to the results of the visual inspection in the inspection assembly 2.

[0108] Example 3

[0109] In this embodiment, a method flow chart of an adaptive control method based on target detection is provided, such as Figure 3 As shown, an adaptive control method based on target detection includes:

[0110] S1. Acquire the electrical signal generated when the injection molding machine discharges the material. The conveying assembly receives the object of the injection molding machine based on the electrical signal generated when the injection molding machine discharges the material and conveys it to the detection assembly;

[0111] S2, after the detection is completed, a folding signal is generated, based on which the detection assembly absorbs the object and moves it to the folding assembly, the folding assembly folds the object to form a finished product, and generates a transmission signal;

[0112] S3, according to the transmission signal, the folding assembly clamps the folded finished product and conveys it to the transmission assembly;

[0113] S4, the conveying assembly conveys the folded finished parts and packages them.

[0114] For the specific content of an adaptive control method based on target detection, please refer to an adaptive control system based on target detection, which will not be described in detail here.

[0115] Example 4

[0116] In this embodiment, a computer device is provided, including a memory and a processor, the memory is used to store instructions, and the processor is used to execute the instructions, so that the computer device executes the steps of implementing the above-mentioned adaptive control method based on target detection.

[0117] Example 5

[0118] In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed, the steps of the above-mentioned adaptive control method based on target detection are implemented.

[0119] The computer-readable storage medium includes: a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and other media for storing program codes.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. An adaptive control system based on target detection, applied to an adaptive control device based on target detection, the adaptive control device comprising a conveying assembly, a detecting assembly and a folding assembly, the conveying assembly is used to receive an object formed by an injection molding machine and convey it to a detection object hole in the detecting assembly, the detecting assembly is used to detect the object and convey the detected object to the folding assembly, and the folding assembly is used to fold the object to form a finished product; Features: The adaptive control system comprises an execution subsystem and a detection subsystem, wherein the execution subsystem is used to control the adaptive control device, and the detection subsystem is used to detect objects; The execution subsystem includes a conveying module and a folding module; The conveying module is used to control the conveying assembly to receive the object and convey it to the detection assembly, and the folding module is used to control the folding assembly to fold the object into a finished product; The detection subsystem includes a target detection module, which is used to detect whether an object located in a detection object hole has an abnormality and determine the type of abnormality. The determination of the abnormality type includes using an edge function to determine an edge border of the object and comparing it with a standard border to determine the abnormality type of the object based on the continuity of the edge border.

2. The adaptive control system based on target detection according to claim 1, characterized in that: The specific steps of detecting whether an object located in the detection object cavity is abnormal include: Acquire the image of the object in the detection object hole in real time to obtain the object image; Configure a standard object image and calculate the difference between the object image and the standard object image; Configure a difference threshold, compare the difference between the object image and the standard object image with the difference threshold, determine whether the object image has an abnormality, obtain the abnormal image and perform image analysis on the abnormal image; Identify the abnormal type of the object, mark the abnormal object, form a sequence list, and generate a folding signal and transmit it to the folding assembly.

3. The adaptive control system based on target detection as claimed in claim 2, characterized in that: The calculation formula of the difference between the object image and the standard object image is as follows: Where dis represents the difference between the object image and the standard object image, p represents the width of the target image, q represents the height of the target image, I1(a, b) represents the pixel value of the object image at position (a, b), I2(a, b) represents the pixel value of the standard object image at position (a, b), a represents the horizontal coordinate, and b represents the vertical coordinate; The logic for determining whether an object image has an abnormality includes: If the difference between the object image and the standard object image is less than or equal to the difference threshold, it means that there is no abnormality in the object image; If the difference between the object image and the standard object image is greater than the difference threshold, it means that there is an abnormality in the object image.

4. The adaptive control system based on target detection as claimed in claim 3, characterized in that: The object includes a force-bearing portion and a hand-holding portion, and the specific steps of identifying the abnormal type of the object include: An edge function is configured, and an edge frame used to characterize the edge of the object in the abnormal image is extracted based on the edge function, and the edge frame is compared with the configured standard frame to determine the abnormal type of the object; If the edge frame is a continuous frame, it is further determined whether there is a fault in the edge frame. If there is a fault, the fault position is identified. If the fault position is in the force-bearing part, the abnormality type of the object is determined to be object fracture; if the fault position is in the hand-held part, the abnormality type of the object is determined to be surface abnormality. If the edge frame is a discontinuous frame, the abnormal type of the object is determined to be a surface abnormality.

5. The adaptive control system based on target detection as claimed in claim 4, characterized in that: Determine whether the object can be aligned with the detection object hole in the detection assembly when being transported by the conveying assembly, and the alignment determination logic includes: Acquire a process of conveying the received object along the conveying assembly to the detection object hole in the detection assembly to obtain a conveying image; Project the conveyed image onto a plane, identify objects and detect the edges of object holes; Points are taken symmetrically along the edges of the object and the detection object hole, and the plane coordinates of the object edge points and the detection object hole edge points are obtained respectively; Calculate the average offset between the edge points of the object and the edge points of the detected object holes; Determine the offset direction of the object and the detection object hole according to the positive and negative values ​​of the average offset between the object edge point and the detection object hole edge point; Configure the offset threshold, compare the average offset of the edge point of the object and the edge point of the detection object hole with the offset threshold to determine whether the object and the detection object hole are offset, and adjust the installation position of the conveying assembly according to the offset direction and the average offset.

6. The adaptive control system based on target detection according to claim 5, characterized in that: The logic for determining whether the object and the detection object hole are offset includes: If the average offset between the edge point of the object and the edge point of the detected object hole is less than or equal to the offset threshold, it is considered that there is no offset between the object and the detected object hole; If the average offset between the edge points of the object and the edge points of the detected object holes is greater than the offset threshold, it is considered that there is an offset between the object and the detected object holes.

7. An adaptive control device based on target detection, used to implement an adaptive control system based on target detection as claimed in any one of claims 1 to 6, characterized in that: include: A machine body (5), a conveying assembly (1), a detection assembly (2) and a folding assembly (3) arranged on the machine body (5); The conveying assembly (1) is used to receive an object from the output end of the injection molding machine and convey it. The detection assembly (2) is used to receive the object conveyed by the conveying assembly (1). The detection assembly (2) is provided with a detection object hole (231). The object is placed in the detection object hole (231) and inspected. When the inspection is completed, the inspected object is conveyed to the folding assembly (3). The folding assembly (3) is used to fold the object and form a finished product.

8. The adaptive control device based on target detection according to claim 7, characterized in that: The conveying assembly (1) comprises a support column (11) and a supporting truss (12), wherein a first power source (111) is arranged on the support column (11), and the supporting truss (12) is connected to the first power source (111). A rotating motor (13) is also arranged at the connection between the supporting truss (12) and the first power source (111), and the rotating motor (13) is used to control the rotation of the supporting truss (12). A supporting suction cup (121) for adsorbing objects is arranged on the supporting truss (12).

9. The adaptive control device based on target detection according to claim 8, characterized in that: The detection assembly (2) comprises a second power source (21), an adsorption truss (22) and a detection carrier (23); a support truss (51) is arranged on the body (5); a third power source (511) is arranged on the support truss (51); the third power source (511) is connected to the second power source (21) via a sliding seat (512); the second power source (21) is arranged on the sliding seat (512); the adsorption truss (22) is slidably connected to the second power source (21); The second power source (21) is used to control the adsorption truss (22) to move toward or away from the detection carrier (23); the detection carrier (23) is arranged on the machine body (5); a detection object hole (231) is provided in the detection carrier (23); an adsorption suction cup (221) for adsorbing an object is arranged on the adsorption truss (22); and a detection module (222) is also arranged on the adsorption truss (22); the detection module (222) is used to perform visual detection on the object in the detection object hole (231); The folding assembly (3) comprises a fourth power source (31), a clamping truss (32) and a folding carrier (33); the fourth power source (31) is connected to the third power source (511) via the sliding seat (512); the fourth power source (31) is arranged on the sliding seat (512); the clamping truss (32) is slidably connected to the fourth power source (31); the folding carrier (33) is arranged on the machine body (5); a folding object hole (331) is arranged on the folding carrier (33); a clamp for clamping an object is arranged on the clamping truss (32); a pushing module (332) is further arranged on the folding carrier (33); the pushing module (332) is used to fold the object in the folding object hole (331) and form a finished product; and the pushing module (332) is provided with a cylinder (3321) for pushing the object in the folding object hole (331) to fold.

10. An adaptive control method based on target detection, implemented based on an adaptive control system based on target detection according to any one of claims 1 to 6, characterized in that: include, An electrical signal generated when the injection molding machine discharges material is obtained, and the conveying assembly receives the object of the injection molding machine based on the electrical signal generated when the injection molding machine discharges material and conveys it to the detection assembly; After the detection is completed, a folding signal is generated. Based on the folding signal, the detection assembly absorbs the object and moves it to the folding assembly, and the folding assembly folds the object to form a finished product.

Images