Turnover system and method special for scrapped motor vehicle

Abstract

The invention provides a special turnover system and method for a scrapped motor vehicle, and the method comprises the steps: obtaining a turnover image of the scrapped motor vehicle through monitoring the turnover process of the scrapped motor vehicle in real time; based on a target detection model in industrial vision and in combination with a turnover image obtained through real-time monitoring, determining dynamic change characteristics of a turnover position of the scrapped motor vehicle in the turnover process, and determining the disturbance influence degree of the turnover process of the scrapped motor vehicle under the industrial vision through the dynamic change characteristics; inertial load information of the mechanical arm at different overturning angles is extracted from the historical operation records, and the posture deviation of the mechanical arm during overturning of the scrapped motor vehicle is determined according to the inertial load information; and according to the disturbance influence degree and the attitude deviation, the active-disturbance-rejection coefficient of the mechanical arm in the overturning process is determined, and the mechanical arm conducts overturning control over the scrapped motor vehicle based on the active-disturbance-rejection coefficient. By the adoption of the scheme, adaptive turnover of the scrapped motor vehicle can be achieved under the complex structure of multiple vehicle types, so that operation errors in the turnover process are reduced.

Description

Technical Field

[0001] The present application relates to the field of automated flipping technology, and more specifically, to a special flipping system and method for scrapped motor vehicles. Background Art

[0002] Scrapped motor vehicles usually contain a large amount of recyclable resources, such as metals, plastics, rubber, etc., but these resources are closely connected within the vehicle structure. Scrapped vehicles are usually flipped under industrial vision to adjust the angle of the scrapped vehicles so that disassembly tools can easily access the target parts, thereby more efficiently disassembling and recycling usable parts.

[0003] When flipping a scrapped motor vehicle under industrial vision, it is necessary to ensure the safety and stability of the vehicle during the flipping process to avoid operational errors or equipment damage due to sliding or displacement. However, in the prior art, the traditional flipping method for scrapped motor vehicles is usually designed for a single model and lacks flexible adjustment capabilities, resulting in poor versatility. Scrapped motor vehicles of different models, sizes and weight distributions pose a challenge to the adaptability of existing flipping methods. Due to the structural complexity of different models, the universal flipping method is difficult to adapt to the diverse vehicle sizes and weight distributions, resulting in inaccurate flipping angle control and insufficient vehicle stability, such as vehicle shaking or accidental overturning, which in turn affects the accuracy and safety of the disassembly operation. Therefore, how to achieve adaptive flipping of scrapped motor vehicles under the complex structure of multiple models to reduce operational errors during the flipping process has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a special turning system and method for scrapped motor vehicles, which can realize adaptive turning of scrapped motor vehicles under the complex structures of multiple models to reduce operational errors during the turning process.

[0005] In a first aspect, the present application provides a method for controlling the rollover of a scrapped motor vehicle, comprising the following steps: The flipping process of the scrapped motor vehicle is monitored in real time by an intelligent camera to obtain a flipping image of the scrapped motor vehicle; Based on the target detection model in industrial vision and the flipping image obtained by real-time monitoring, the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process are determined, and the disturbance influence degree of the flipping process of the scrapped motor vehicle under industrial vision is determined through the dynamic change characteristics; Acquire historical operation records of the mechanical arm flipping the scrapped motor vehicle, extract inertial load information of the mechanical arm at different flipping angles from the historical operation records, and determine the posture deviation of the mechanical arm when flipping the scrapped motor vehicle according to the inertial load information and structural characteristics of the scrapped motor vehicle; The self-disturbance rejection coefficient of the robot arm during the flipping process is determined according to the disturbance influence degree and the posture deviation, and the robot arm performs flipping control on the scrapped motor vehicle based on the self-disturbance rejection coefficient.

[0006] In some embodiments, determining the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process based on the target detection model in industrial vision combined with the flipping image obtained by real-time monitoring specifically includes: The target detection model in industrial vision is combined with the flipped image obtained by real-time monitoring to perform position recognition and obtain the spatial position data of the scrapped motor vehicle during the flipping process; Generating a dynamic change curve of the flipping position of the scrapped motor vehicle during the flipping process according to the spatial position data; The dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process are extracted from the dynamic change curve.

[0007] In some embodiments, determining the disturbance influence degree of the rollover process of the scrapped motor vehicle under industrial vision by using the dynamic change characteristics specifically includes: Determine the ideal change trajectory of the flipping position of the scrapped motor vehicle during the flipping process; The disturbance influence degree of the rollover process of the scrapped motor vehicle under industrial vision is determined by the ideal change trajectory and the dynamic change characteristics.

[0008] In some embodiments, extracting the inertial load information of the robot arm at different flip angles from the historical operation record specifically includes: Extracting force data when the robot arm performs each flip angle from the historical operation record; All force data are fitted to obtain the inertial load information of the robot arm at different flip angles.

[0009] In some embodiments, determining the self-disturbance rejection coefficient of the robotic arm during the flipping process according to the disturbance influence degree and the posture deviation specifically includes: Determining a feedforward compensation amount of the mechanical arm for the rollover process of the scrapped motor vehicle according to the disturbance influence degree; Determining the feedback adjustment amount of the mechanical arm during the flipping process of the scrapped motor vehicle through the posture deviation; The self-disturbance rejection coefficient of the robot arm during the flipping process is determined by the feedforward compensation amount and the feedback adjustment amount.

[0010] In some embodiments, the mechanical arm performs flipping control on the scrapped motor vehicle based on the self-disturbance rejection coefficient, specifically comprising: Obtaining a current gain coefficient of the controller of the robotic arm; Adjusting the current gain coefficient according to the self-disturbance rejection coefficient; The mechanical arm controls the overturning of the scrapped motor vehicle through the adjusted gain coefficient.

[0011] In some embodiments, historical operation records of a robotic arm flipping a scrapped motor vehicle are obtained from an industrial database.

[0012] In a second aspect, the present application provides a dedicated rollover system for scrapped motor vehicles, including a rollover control unit, wherein the rollover control unit includes: A visual monitoring module is used to monitor the rollover process of the scrapped motor vehicle in real time through an intelligent camera to obtain a rollover image of the scrapped motor vehicle; A processing module, for determining the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process based on the target detection model in the industrial vision and the flipping image obtained by real-time monitoring, and determining the disturbance influence degree of the flipping process of the scrapped motor vehicle under the industrial vision through the dynamic change characteristics; The processing module is further used to obtain historical operation records of the mechanical arm flipping the scrapped motor vehicle, extract inertial load information of the mechanical arm at different flipping angles from the historical operation records, and determine the posture deviation of the mechanical arm when flipping the scrapped motor vehicle according to the inertial load information and the structural characteristics of the scrapped motor vehicle; An execution module is used to determine the self-disturbance rejection coefficient of the mechanical arm during the flipping process according to the disturbance influence degree and the posture deviation, and the mechanical arm performs flipping control on the scrapped motor vehicle based on the self-disturbance rejection coefficient.

[0013] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned method for controlling the rollover of a scrapped motor vehicle.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions or codes, and when the instructions or codes are run on a computer, the computer implements the above-mentioned method for controlling the rollover of scrapped motor vehicles when executing the computer.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: In the present application, a flipping process of a scrapped motor vehicle is monitored in real time by an intelligent camera to obtain a flipping image of the scrapped motor vehicle; based on a target detection model in industrial vision and the flipping image obtained by real-time monitoring, the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process are determined, and the disturbance influence degree of the flipping process of the scrapped motor vehicle under industrial vision is determined through the dynamic change characteristics; the historical operation record of a robotic arm flipping the scrapped motor vehicle is obtained, and the inertial load information of the robotic arm at different flipping angles is extracted from the historical operation record, and the posture deviation of the robotic arm when flipping the scrapped motor vehicle is determined according to the inertial load information and the structural characteristics of the scrapped motor vehicle; the self-disturbance rejection coefficient of the robotic arm during the flipping process is determined according to the disturbance influence degree and the posture deviation, and the robotic arm performs flipping control on the scrapped motor vehicle based on the self-disturbance rejection coefficient.

[0016] It can be seen that in the present application, firstly, the disturbance influence degree of the flipping process of the scrapped motor vehicle under industrial vision is determined by the dynamic change characteristics, so as to provide compensation data support for the flipping process, so that the flipping process can adapt to non-ideal environments and vehicles with different structures; secondly, the posture deviation of the mechanical arm when flipping the scrapped motor vehicle is determined according to the inertial load information and the structural characteristics of the scrapped motor vehicle, and by determining the posture deviation, the mechanical arm can dynamically adjust the flipping action to avoid flipping failure or instability caused by differences in the structure of various vehicles; then, the mechanical arm is determined according to the disturbance influence degree and the posture deviation when flipping. The self-disturbance rejection coefficient in the process is used to enhance the adaptability of the robot arm to flip the scrapped motor vehicle through the self-disturbance rejection system, so that the robot arm can adapt to the dynamic changes in the flipping process in real time; finally, the robot arm controls the flipping of the scrapped motor vehicle based on the self-disturbance rejection coefficient, and dynamically adjusts the control of the flipping process based on the self-disturbance rejection coefficient to optimize the real-time response capability of the robot arm to the flipping process, so that the flipping action is more precise and the flipping vibration or vehicle slipping caused by mismatched flipping control is reduced; in summary, the scheme can realize the adaptive flipping of scrapped motor vehicles under the complex structure of multiple models to reduce the operational errors in the flipping process. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] Figure 1 is an exemplary flow chart of a method for controlling a rollover of a scrapped motor vehicle according to some embodiments of the present application; Figure 2 is an exemplary flow chart of determining posture deviation according to some embodiments of the present application; Figure 3 is an exemplary flow chart of determining an auto-disturbance rejection coefficient according to some embodiments of the present application; Figure 4 is a schematic diagram of the structure of a flip control unit according to some embodiments of the present application; Figure 5 It is a structural schematic diagram of a computer device for implementing a method for controlling the rollover of a scrapped motor vehicle according to some embodiments of the present application. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] refer to Figure 1 , which is an exemplary flow chart of a method for controlling the rollover of a scrapped motor vehicle according to some embodiments of the present application. The method 100 for controlling the rollover of a scrapped motor vehicle mainly includes the following steps: In step 101, the flipping process of the scrapped motor vehicle is monitored in real time by a smart camera to obtain a flipping image of the scrapped motor vehicle.

[0021] In specific implementation, the flipping process of the scrapped motor vehicle can be monitored in real time by a smart camera, and the flipping image of the scrapped motor vehicle during the flipping process can be collected in real time at a specified frequency, wherein the specified frequency can be set according to the flipping speed of the scrapped motor vehicle, for example: if the flipping speed is slow (such as 1° / second), the specified frequency can be set lower (such as 5-10 frames / second); if the flipping speed is fast (such as 10° / second), the specified frequency needs to be set higher (such as 30 frames / second and above). In other embodiments, other methods can also be used for setting, which is not specifically limited here.

[0022] It should be noted that the flip image in the present application reflects the change in the flip position of the scrapped motor vehicle.

[0023] In step 102, based on the target detection model in industrial vision and the flipping image obtained by real-time monitoring, the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process are determined, and the disturbance influence degree of the flipping process of the scrapped motor vehicle under industrial vision is determined through the dynamic change characteristics.

[0024] In some embodiments, the following steps can be used to determine the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process based on the target detection model in industrial vision combined with the flipping image obtained by real-time monitoring: The target detection model in industrial vision is combined with the flipped image obtained by real-time monitoring to perform position recognition and obtain the spatial position data of the scrapped motor vehicle during the flipping process; Generating a dynamic change curve of the flipping position of the scrapped motor vehicle during the flipping process according to the spatial position data; The dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process are extracted from the dynamic change curve.

[0025] In specific implementation, position recognition is performed through the target detection model in industrial vision combined with the flip image obtained by real-time monitoring, and the spatial position data of the scrapped motor vehicle during the flipping process can be obtained in the following manner, namely: the real-time position state of the scrapped motor vehicle during the flipping process is recognized and located based on the flip image obtained by real-time monitoring through the target detection model in industrial vision, and the position state is, for example, flip angle, tilt angle, displacement and center position, etc. Each position state corresponds to a positioning time, and all the recognized position states are combined into the spatial position data of the scrapped motor vehicle during the flipping process; the dynamic position of the flipping position of the scrapped motor vehicle during the flipping process is generated according to the spatial position data. The dynamic change curve can be realized in the following manner, that is, a dynamic change curve of the flipping position of the scrapped motor vehicle during the flipping process can be generated based on the spatial position data through a drawing tool (such as Matplotlib, Matlab, etc.), wherein the positioning time is used as the horizontal axis and the position state (such as the flipping angle) is used as the vertical axis; extracting the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process from the dynamic change curve can be realized in the following manner, that is, the trend change (such as the slope) of the dynamic change curve can be used as the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process; in other embodiments, other methods can also be used for determination, which is not limited here.

[0026] It should be noted that the spatial position data in the present application represents a numerical set of the real-time position status of the scrapped motor vehicle during the flipping process; the dynamic change curve represents a curve formed by the spatial position data, reflecting the changing trend of the flipping position of the scrapped motor vehicle during the flipping process.

[0027] In addition, it should be noted that the dynamic change characteristics in the present application characterize the speed of change of the flipping position of the scrapped motor vehicle during the flipping process. The larger the numerical value corresponding to the dynamic change characteristics, the faster the change of the flipping position of the scrapped motor vehicle during the flipping process. The smaller the numerical value corresponding to the dynamic change characteristics, the slower the change of the flipping position of the scrapped motor vehicle during the flipping process.

[0028] In some embodiments, determining the disturbance influence degree of the rollover process of the scrapped motor vehicle under industrial vision by using the dynamic change characteristics can be achieved by using the following steps: Determine the ideal change trajectory of the flipping position of the scrapped motor vehicle during the flipping process; The disturbance influence degree of the rollover process of the scrapped motor vehicle under industrial vision is determined by the ideal change trajectory and the dynamic change characteristics.

[0029] In specific implementation, the ideal change trajectory represents the trajectory of the flip position of the scrapped motor vehicle changing with time without external disturbance; determining the ideal change trajectory of the flip position during the flipping process of the scrapped motor vehicle can be achieved in the following manner, namely: a curve of the change trajectory of the flip position of the scrapped motor vehicle over time under ideal conditions can be generated based on the known starting point, end point and flip path requirements of the flip position of the scrapped motor vehicle and the flip kinematics principle through machine learning, so as to obtain the ideal change trajectory of the flip position during the flipping process of the scrapped motor vehicle, wherein the horizontal axis in the ideal change trajectory represents time and the vertical axis represents the flip position; determining the disturbance influence degree of the flipping process of the scrapped motor vehicle under industrial vision by the ideal change trajectory and the dynamic change feature can be achieved in the following manner, namely: the change rate between each adjacent flip position in the ideal change trajectory can be calculated, wherein two corresponding flip positions adjacent in time are taken as adjacent flip positions, and then the absolute difference between each change rate and the value corresponding to the dynamic change feature is calculated, and finally the average value of all the calculated absolute differences is taken as the disturbance influence degree of the flipping process of the scrapped motor vehicle under industrial vision. In other embodiments, other methods can also be used for determination, which is not limited here.

[0030] It should be noted that the disturbance influence degree in the present application reflects the degree of disturbance to the industrial visual monitoring flipping position during the flipping process of the scrapped motor vehicle. The greater the disturbance influence degree, the greater the degree of disturbance to the industrial visual monitoring flipping position during the flipping process of the scrapped motor vehicle. The smaller the disturbance influence degree, the smaller the degree of disturbance to the industrial visual monitoring flipping position during the flipping process of the scrapped motor vehicle.

[0031] In step 103, historical operation records of the robot arm flipping the scrapped motor vehicle are obtained, inertial load information of the robot arm at different flipping angles is extracted from the historical operation records, and the posture deviation of the robot arm when flipping the scrapped motor vehicle is determined based on the inertial load information and the structural characteristics of the scrapped motor vehicle.

[0032] It should be noted that in the present application, stress sensors and displacement sensors are installed on the mechanical arm used to flip scrapped motor vehicles to record the operating data of the mechanical arm during the flipping process. The operating data includes the force data of the mechanical arm at each flipping angle, the relationship between the flipping angle and time, the angular velocity and angular acceleration of the operation, etc., and then all the operating data are stored in the industrial database.

[0033] In specific implementation, the historical operation record of the robotic arm flipping the scrapped motor vehicle can be obtained in the following way, that is: the operation data of the robotic arm used to flip the scrapped motor vehicle during the flipping process in the past six months can be obtained from the industrial database, and all the obtained operation data will constitute the historical operation record of the robotic arm flipping the scrapped motor vehicle.

[0034] It should be noted that the historical operation record in the present application represents a collection of all operation data of the robot arm flipping over scrapped motor vehicles in the past period of time.

[0035] In some embodiments, extracting the inertial load information of the robot arm at different flip angles from the historical operation record can be achieved by using the following steps: Extracting force data when the robot arm performs each flip angle from the historical operation record; All force data are fitted to obtain the inertial load information of the robot arm at different flip angles.

[0036] In specific implementation, extracting the force data of the robotic arm when executing each flip angle from the historical operation record can be implemented in the following manner, namely: extracting the force data of the robotic arm at each flip angle from the historical operation record, the force data including: load torque, acceleration and inertial force, etc.; fitting all the force data to obtain the inertial load information of the robotic arm at different flip angles can be implemented in the following manner, namely: a fitting model can be established based on historical empirical data through a machine learning algorithm (such as support vector regression (SVR) or a neural network), the fitting model reflects the relationship between the flip angle and the inertial load information of the robotic arm during the flipping process, and then all the force data are fitted through the fitting model, namely: the force data at each flip angle is used as the input of the fitting model, and the output of the fitting model is used as the inertial load information of the robotic arm at different flip angles; other methods can also be used for determination in other embodiments, which are not limited here.

[0037] It should be noted that the force data in the present application represents the force information received by the robotic arm during the flipping process; in addition, the inertial load information represents the dynamic force generated by the load and the rotational inertia of the robotic arm itself during the flipping process.

[0038] In some embodiments, reference Figure 2 As shown in FIG. 1 , this figure is an exemplary flow chart of determining the posture deviation in some embodiments of the present application. In this embodiment, the posture deviation when the mechanical arm flips the scrapped motor vehicle according to the inertial load information and the structural characteristics of the scrapped motor vehicle can be determined by the following steps: First, in step 1031, the structural characteristics of the scrapped motor vehicle are obtained; Secondly, in step 1032, a posture error matrix of the scrapped motor vehicle during the flipping process is determined according to the inertial load information and the structural features; Finally, in step 1033, the posture deviation of the robot arm when flipping the scrapped motor vehicle is determined by the posture error matrix.

[0039] In specific implementation, the structural features in this application reflect the physical properties of the shape and structure of the scrapped motor vehicle. The structural features of the scrapped motor vehicle can be obtained in the following manner, namely: the structural features of the scrapped motor vehicle can be obtained through industrial vision, and the structural features include: the geometric shape, weight distribution and center of gravity position of the scrapped motor vehicle, etc. In other embodiments, other methods can also be used to obtain, which is not specifically limited here.

[0040] It should be noted that the posture error matrix represents the deviation between the actual posture (position and direction) of the scrapped motor vehicle and the theoretical posture. The posture error matrix can be used to quantify the offset and rotation errors of the scrapped motor vehicle during the flipping process. As a preferred embodiment, the posture error matrix of the scrapped motor vehicle during the flipping process is determined according to the inertial load information and the structural features. It can be implemented in the following way, namely: first, a posture description model of the scrapped motor vehicle during the flipping process is constructed based on the inertial load information, the structural features and the flipping angle of the scrapped motor vehicle during the flipping process through a dynamic simulation algorithm, and then the actual posture of the scrapped motor vehicle at each flipping angle during the flipping process is determined based on the posture description model, and the scrapped motor vehicle during the flipping process is composed. The actual posture matrix of the process is calculated, and the actual posture matrix is ​​composed of numerical values. Subsequently, the ideal posture matrix of the scrapped motor vehicle in the flipping process without external interference is calculated by an existing dynamic model, and the ideal posture matrix is ​​composed of numerical values. Finally, the actual posture matrix is ​​multiplied by the inverse matrix of the ideal posture matrix, and the matrix obtained by the multiplication is used as the posture error matrix of the scrapped motor vehicle during the flipping process; determining the posture deviation of the mechanical arm flipping the scrapped motor vehicle through the posture error matrix can be achieved in the following way, that is, the square root of the sum of the squares of all the numerical values ​​in the posture error matrix can be used as the posture deviation of the mechanical arm flipping the scrapped motor vehicle; in other embodiments, other methods can also be used for determination, which is not limited here.

[0041] It should be noted that the posture deviation in the present application reflects the degree of deviation between the actual posture controlled by the robot arm when flipping a scrapped motor vehicle and the expected target. The larger the posture deviation, the greater the deviation between the actual posture controlled by the robot arm when flipping a scrapped motor vehicle and the expected target. The smaller the posture deviation, the smaller the deviation between the actual posture controlled by the robot arm when flipping a scrapped motor vehicle and the expected target. It will not be repeated here.

[0042] In step 104, the self-disturbance rejection coefficient of the robot arm during the flipping process is determined according to the disturbance influence degree and the posture deviation, and the robot arm performs flipping control on the scrapped motor vehicle based on the self-disturbance rejection coefficient.

[0043] In some embodiments, determining the self-disturbance rejection coefficient of the robotic arm during the flipping process according to the disturbance influence degree and the posture deviation can be implemented by the following steps: Determining a feedforward compensation amount of the mechanical arm for the rollover process of the scrapped motor vehicle according to the disturbance influence degree; Determining the feedback adjustment amount of the mechanical arm during the flipping process of the scrapped motor vehicle through the posture deviation; The self-disturbance rejection coefficient of the robot arm during the flipping process is determined by the feedforward compensation amount and the feedback adjustment amount.

[0044] In specific implementation, the feedforward compensation amount in the present application represents the degree of compensation for the disturbance influence degree during the process of the robot arm flipping the scrapped motor vehicle; the feedforward compensation amount of the robot arm for the flipping process of the scrapped motor vehicle according to the disturbance influence degree can be implemented in the following manner, that is, an optimization algorithm (such as a genetic algorithm) can be used to find the best feedforward compensation amount for the flipping process of the scrapped motor vehicle based on the disturbance influence degree, and the best result obtained is used as the feedforward compensation amount of the robot arm for the flipping process of the scrapped motor vehicle. In other embodiments, other methods can also be used for determination, which is not limited here; the feedback adjustment amount of the robot arm for the flipping process of the scrapped motor vehicle can be determined by the posture deviation, that is, the feedback adjustment amount of the robot arm for the flipping process of the scrapped motor vehicle can be calculated based on the posture deviation through the proportional-integral-differential control (PID control) in the prior art. In other embodiments, other methods can also be used for determination, which is not limited here; in addition, it should be noted that the feedback adjustment amount represents the degree of correction of the posture deviation during the process of the robot arm flipping the scrapped motor vehicle.

[0045] It should be noted that the self-disturbance rejection coefficient in the present application is an indicator for actively compensating for interference during the process of the robot arm flipping the scrapped motor vehicle. The self-disturbance rejection coefficient can be used to guide the robot arm to adjust the flipping action and improve the stability of the flipping process. As a preferred embodiment, the self-disturbance rejection coefficient of the robot arm during the flipping process is determined by the feedforward compensation amount and the feedback adjustment amount. The following method can be used, namely: the sum obtained by adding the feedforward compensation amount and the feedback adjustment amount is used as the self-disturbance rejection coefficient of the robot arm during the flipping process, and reference is made to Figure 3 As shown, this figure is an exemplary flow chart for determining the self-disturbance rejection coefficient in some embodiments of the present application. In other embodiments, other methods can also be used for determination, which is not limited here.

[0046] In some embodiments, the mechanical arm can perform flipping control on the scrapped motor vehicle based on the self-disturbance rejection coefficient by adopting the following steps: Obtaining a current gain coefficient of the controller of the robotic arm; Adjusting the current gain coefficient according to the self-disturbance rejection coefficient; The mechanical arm controls the overturning of the scrapped motor vehicle through the adjusted gain coefficient.

[0047] In the specific implementation, first, the current gain coefficient of the controller of the robotic arm is obtained through the robotic arm controller interface, and secondly, the current gain coefficient is adjusted by the self-disturbance rejection coefficient, for example: the self-disturbance rejection coefficient is multiplied by the current gain coefficient, and finally, the adjusted gain coefficient is applied to the controller of the robotic arm to implement the flipping control of the scrapped motor vehicle. Other methods can also be used to implement it in other embodiments, which are not limited here.

[0048] It should be noted that dynamically adjusting the robot control response through the self-disturbance rejection coefficient can effectively offset the deviation caused by the disturbance and optimize the adaptability of the robot to different loads and flip angles, thereby avoiding flip failure or vehicle damage caused by improper flipping.

[0049] In addition, in another aspect of the present application, in some embodiments, the present application provides a dedicated rollover system for scrapped motor vehicles, the system also includes a rollover control unit, referring to Figure 4 , which is a schematic diagram of the structure of a flip control unit according to some embodiments of the present application, the flip control unit 400 includes: a visual monitoring module 401, a processing module 402 and an execution module 403, which are described as follows: Visual monitoring module 401, in this application, the visual monitoring module 401 is mainly used to monitor the flipping process of the scrapped motor vehicle in real time through a smart camera to obtain a flipping image of the scrapped motor vehicle; Processing module 402, in this application, the processing module 402 is mainly used to determine the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process based on the target detection model in industrial vision combined with the flipping image obtained by real-time monitoring, and determine the disturbance influence degree of the flipping process of the scrapped motor vehicle under industrial vision through the dynamic change characteristics; The processing module 402 in the present application is also used to obtain historical operation records of the mechanical arm flipping the scrapped motor vehicle, extract inertial load information of the mechanical arm at different flipping angles from the historical operation records, and determine the posture deviation of the mechanical arm when flipping the scrapped motor vehicle according to the inertial load information and the structural characteristics of the scrapped motor vehicle; The execution module 403 in the present application is mainly used to determine the self-disturbance rejection coefficient of the robotic arm during the flipping process according to the disturbance influence degree and the posture deviation, and the robotic arm performs flipping control on the scrapped motor vehicle based on the self-disturbance rejection coefficient.

[0050] The above describes in detail an example of a dedicated flipping system and method for scrapped motor vehicles provided in an embodiment of the present application. It can be understood that in order to realize the above functions, the corresponding device includes a hardware structure and / or software module corresponding to each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware 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 be beyond the scope of the present application.

[0051] In some embodiments, the present application also provides a computer device, which includes a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned scrapped motor vehicle rollover control method.

[0052] In some embodiments, reference Figure 5 The dotted line in the figure indicates that the unit or module is optional. The figure is a schematic diagram of the structure of a computer device for implementing the scrapped motor vehicle rollover control method of the present application. The scrapped motor vehicle rollover control method in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device 500 can be a terminal device, a server or a chip.

[0053] The processor 501 may be a general-purpose processor or a special-purpose processor. For example, the processor 501 may be a central processing unit (CPU), which may be used to control the computer device 500, execute software programs, and process data of the software programs. The computer device 500 may also include a communication unit 505 to implement signal input (reception) and output (transmission).

[0054] For example, the computer device 500 may be a chip, the communication unit 505 may be an input and / or output circuit of the chip, or the communication unit 505 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other devices.

[0055] For another example, the computer device 500 may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0056] The computer device 500 may include one or more memories 502, on which a program 504 is stored. The program 504 can be executed by the processor 501 to generate instructions 503, so that the processor 501 performs the method described in the above method embodiment according to the instructions 503. Optionally, data (such as a target audit model) can also be stored in the memory 502. Optionally, the processor 501 can also read the data stored in the memory 502, and the data can be stored at the same storage address as the program 504, or the data can be stored at a different storage address from the program 504.

[0057] The processor 501 and the memory 502 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0058] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 501. The processor 501 can be a CPU, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0059] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0060] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned method for controlling the rollover of scrapped motor vehicles when executing the computer.

[0061] In summary, in the dedicated flipping system and method for scrapped motor vehicles disclosed in the embodiment of the present application, the flipping process of the scrapped motor vehicle is monitored in real time by an intelligent camera to obtain a flipping image of the scrapped motor vehicle; based on the target detection model in industrial vision and the flipping image obtained by real-time monitoring, the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process are determined, and the disturbance influence degree of the flipping process of the scrapped motor vehicle under industrial vision is determined by the dynamic change characteristics; the historical operation record of the robotic arm flipping the scrapped motor vehicle is obtained, and the inertial load information of the robotic arm at different flipping angles is extracted from the historical operation record, and the posture deviation of the robotic arm when flipping the scrapped motor vehicle is determined according to the inertial load information and the structural characteristics of the scrapped motor vehicle; the self-disturbance rejection coefficient of the robotic arm during the flipping process is determined according to the disturbance influence degree and the posture deviation, and the robotic arm performs flipping control on the scrapped motor vehicle based on the self-disturbance rejection coefficient; the adaptive flipping of scrapped motor vehicles can be achieved under the complex structure of multiple models to reduce the operation error during the flipping process.

[0062] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0063] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for controlling the rollover of a scrapped motor vehicle, characterized in that: The steps include: The flipping process of the scrapped motor vehicle is monitored in real time by an intelligent camera to obtain a flipping image of the scrapped motor vehicle; Based on the target detection model in industrial vision and the flipping image obtained by real-time monitoring, the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process are determined, and the disturbance influence degree of the flipping process of the scrapped motor vehicle under industrial vision is determined through the dynamic change characteristics; Acquire historical operation records of the mechanical arm flipping the scrapped motor vehicle, extract inertial load information of the mechanical arm at different flipping angles from the historical operation records, and determine the posture deviation of the mechanical arm when flipping the scrapped motor vehicle according to the inertial load information and structural characteristics of the scrapped motor vehicle; The self-disturbance rejection coefficient of the robot arm during the flipping process is determined according to the disturbance influence degree and the posture deviation, and the robot arm performs flipping control on the scrapped motor vehicle based on the self-disturbance rejection coefficient.

2. The method according to claim 1, characterized in that Based on the target detection model in industrial vision and the flip image obtained by real-time monitoring, the dynamic change characteristics of the flip position of the scrapped motor vehicle during the flip process are determined, including: The target detection model in industrial vision is combined with the flipped image obtained by real-time monitoring to perform position recognition and obtain the spatial position data of the scrapped motor vehicle during the flipping process; Generating a dynamic change curve of the flipping position of the scrapped motor vehicle during the flipping process according to the spatial position data; The dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process are extracted from the dynamic change curve.

3. The method according to claim 1, characterized in that Determining the disturbance influence degree of the rollover process of scrapped motor vehicles under industrial vision by using the dynamic change characteristics specifically includes: Determine the ideal change trajectory of the flipping position of the scrapped motor vehicle during the flipping process; The disturbance influence degree of the rollover process of the scrapped motor vehicle under industrial vision is determined by the ideal change trajectory and the dynamic change characteristics.

4. The method according to claim 1, characterized in that Extracting the inertial load information of the robot arm at different flip angles from the historical operation record specifically includes: Extracting force data when the robot arm performs each flip angle from the historical operation record; All force data are fitted to obtain the inertial load information of the robot arm at different flip angles.

5. The method according to claim 1, characterized in that Determining the self-disturbance rejection coefficient of the robot arm during the flipping process according to the disturbance influence degree and the posture deviation specifically includes: Determining a feedforward compensation amount of the mechanical arm for the rollover process of the scrapped motor vehicle according to the disturbance influence degree; Determining the feedback adjustment amount of the mechanical arm during the flipping process of the scrapped motor vehicle through the posture deviation; The self-disturbance rejection coefficient of the robot arm during the flipping process is determined by the feedforward compensation amount and the feedback adjustment amount.

6. The method according to claim 1, characterized in that The mechanical arm performs the flipping control on the scrapped motor vehicle based on the self-disturbance rejection coefficient, specifically comprising: Obtaining a current gain coefficient of the controller of the robotic arm; Adjusting the current gain coefficient according to the self-disturbance rejection coefficient; The mechanical arm controls the overturning of the scrapped motor vehicle through the adjusted gain coefficient.

7. The method according to claim 1, characterized in that The historical operation records of the robotic arm flipping scrapped motor vehicles are obtained from the industrial database.

8. A special rollover system for scrapped motor vehicles, comprising a rollover control unit, characterized in that: The flip control unit comprises: A visual monitoring module is used to monitor the rollover process of the scrapped motor vehicle in real time through an intelligent camera to obtain a rollover image of the scrapped motor vehicle; A processing module, for determining the dynamic change characteristics of the flipping position of the scrapped motor vehicle during the flipping process based on the target detection model in the industrial vision and the flipping image obtained by real-time monitoring, and determining the disturbance influence degree of the flipping process of the scrapped motor vehicle under the industrial vision through the dynamic change characteristics; The processing module is further used to obtain historical operation records of the mechanical arm flipping the scrapped motor vehicle, extract inertial load information of the mechanical arm at different flipping angles from the historical operation records, and determine the posture deviation of the mechanical arm when flipping the scrapped motor vehicle according to the inertial load information and the structural characteristics of the scrapped motor vehicle; An execution module is used to determine the self-disturbance rejection coefficient of the mechanical arm during the flipping process according to the disturbance influence degree and the posture deviation, and the mechanical arm performs flipping control on the scrapped motor vehicle based on the self-disturbance rejection coefficient.

9. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the method for controlling the rollover of a scrapped motor vehicle according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions or codes, and when the instructions or codes are executed on a computer, the computer implements the method for controlling the rollover of a scrapped motor vehicle as claimed in any one of claims 1 to 7.

Images