Intelligent driving system of intelligent industrial robot arm

Abstract

The application relates to the technical field of mechanical arm driving, and discloses an intelligent driving system of an intelligent industrial mechanical arm, which comprises a mechanical arm, a data acquisition module and an intelligent driving module. The intelligent driving system of the intelligent industrial mechanical arm collects data sets by establishing a three-dimensional coordinate system through the data acquisition module, so that accurate positioning and path optimization are facilitated; the intelligent driving module classifies target objects according to cross-sectional shapes, generates corresponding recognition areas, quickly adapts to dynamic sorting scenes, analyzes and generates driving distances between driving ends and target objects, and optimizes moving paths in a coherent manner; the intelligent driving module analyzes the pressure change degree of the mechanical arm driving end, generates a corresponding fluctuation rate, and avoids target object sliding; multidimensional collaborative control has high accuracy; the intelligent driving module is provided with a fixed threshold value, can evaluate the grabbing grades of different types of target objects, select optimal cross-sectional contact points, monitor the grabbing state of the mechanical arm driving end, generate corresponding driving suggestions, and has high production efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mechanical arm driving, in particular to an intelligent driving system of an intelligent industrial mechanical arm. BACKGROUND

[0002] An intelligent industrial mechanical arm is a machine device that can imitate human arm movement. Through high-precision sensors, advanced control systems, and powerful actuators, it can achieve tasks such as grabbing, carrying, operating, and placing various workpieces. Its structure usually includes a base, an arm, joints, and an end effector. The base provides stable support for the mechanical arm, ensuring its stability during work. The arm can flexibly stretch and rotate like a human arm. The joints are the key parts connecting each part, allowing the mechanical arm to move in multiple dimensions through precise control. The end effector is designed in various shapes and functions, such as grippers, suction cups, and welding heads, to meet the operational needs of different scenarios. In terms of sorting function, the intelligent industrial mechanical arm has very high sorting accuracy. By equipping advanced visual recognition systems and high-precision position sensors, the mechanical arm can accurately identify workpieces of different shapes, sizes, and materials and sort them according to pre-set rules. Whether it is a small electronic component or a large mechanical part, it can be precisely grabbed and placed at the designated location, greatly improving the accuracy and efficiency of sorting. The sorting function of the intelligent industrial mechanical arm is widely used in many industries. In the logistics industry, it can be used for sorting and distributing express packages, improving logistics efficiency. In the manufacturing industry, it can classify and assemble parts to ensure product quality. In the food industry, it can sort and package food to ensure food safety.

[0003] Currently, the intelligent driving system of traditional industrial mechanical arms has poor environmental adaptability, making it difficult to adapt to dynamic sorting scenarios in real time. The motion trajectory has deviations, and the sorting efficiency and accuracy are low. In addition, during the process of grabbing target objects by the mechanical arm, it is difficult to timely detect missed grabbing and slipping problems. SUMMARY

[0004] (I) Technical problems solved

[0005] To address the shortcomings of the prior art, the present application provides an intelligent driving system of an intelligent industrial mechanical arm, which has the advantages of high multi-dimensional collaborative control precision and high-efficiency driving production efficiency, solving the problems of poor environmental adaptability of the intelligent driving system of traditional industrial mechanical arms and the difficulty in timely detecting missed grabbing and slipping.

[0006] (II) Technical solutions

[0007] In order to achieve the above object, the application provides the following technical scheme: an intelligent driving system of an intelligent industrial robot arm, comprising a robot arm, a data acquisition module and an intelligent driving module;

[0008] The robot arm comprises a fixed end, a large arm, a joint movable end, a small arm and a driving end, the fixed end is used for fixedly mounting the robot arm, the joint movable end is used for driving the large arm and the small arm, and the driving end is provided with a clamping gripper for grabbing a target object.

[0009] The data acquisition module establishes a three-dimensional coordinate system Z with the fixed end as the origin, the data acquisition module comprises a scanning data unit, a driving data unit and a sensing data unit, the scanning data unit collects a target data set by connecting an infrared camera through a network, the target data set comprises scanning data of the target object, the driving data unit collects a driving data set according to the three-dimensional coordinate system Z, the driving data set comprises coordinate data of all nodes, and the sensing data unit collects a sensing data set by connecting a sensing device through a network, the sensing data set comprises pressure data of the driving end of the robot arm.

[0010] The intelligent driving module comprises a target recognition unit, a distance evaluation unit, a pressure monitoring unit and a driving management unit, the target recognition unit classifies the target object according to the cross-sectional shape according to the target data set, and generates a corresponding recognition area Smj, the distance evaluation unit analyzes and generates a driving distance Qdj between the driving end and the target object according to the driving data unit, the pressure monitoring unit analyzes the pressure change degree of the driving end of the robot arm according to the sensing data set, and generates a corresponding fluctuation rate Bdl, and the driving management unit is provided with a fixed range of fluctuation threshold BDY, and in combination with the recognition area Smj, the driving distance Qdj and the fluctuation rate Bdl, the grabbing grade of different kinds of target objects is evaluated, the optimal cross-sectional contact point is selected, the grabbing state of the driving end of the robot arm is monitored, and a corresponding driving suggestion is generated.

[0011] Preferably, the expression of the target data set is {M1, M2, M3,..., Mn}, M1 to Mn represent the scanning data of the first to the n-th target object, and the scanning data comprises the cross-sectional shape and the cross-sectional size.

[0012] Preferably, the expression of the driving data set is {J1, J2, J3,..., Je}, J1 to Je represent the coordinate data of the first to the e-th node, and the node comprises a moving point of the driving end and a cross-sectional contact point of the target object.

[0013] Preferably, the expression of the sensing data set is {Y1, Y2, Y3,..., Yv}, Y1 to Yv represent the pressure values of the first to the v-th time points.

[0014] Preferably, the identification area Smj calculation process is as follows:

[0015] According to the target data set, the target objects are classified according to the cross-sectional shape, wherein the target objects with a circular cross-sectional shape are A-type target objects, and the target objects with a square cross-sectional shape are B-type target objects,

[0016]

[0017] In the formula, r a represents the cross-sectional radius of the a-th target object, the cross-sectional shape of the a-th target object is circular, A represents the number of target objects with a circular cross-sectional shape, represents the total area of all target objects with a circular cross-sectional shape, l b represents the cross-sectional length of the b-th target object, k b represents the cross-sectional width of the b-th target object, the cross-sectional shape of the b-th target object is square, and B represents the number of target objects with a square cross-sectional shape, represents the total area of all target objects with a square cross-sectional shape, s c represents the cross-sectional side length of the c-th target object, h c represents the height of the c-th target object perpendicular to sc, the cross-sectional shape of the c-th target object is triangular, and C represents the number of target objects with a triangular cross-sectional shape, represents the total area of all target objects with a triangular cross-sectional shape.

[0018] Preferably, the driving distance Qdj calculation process is as follows:

[0019] According to the driving data set, the coordinates of the f-th moving point are marked as Jf(x f ,y f ,z f ), and the coordinates of the g-th cross-sectional contact point are marked as Jg(x g ,y g ,z g );

[0020]

[0021] In the formula, represents the straight-line distance from the f-th moving point to the g-th cross-sectional contact point, which is the driving distance Qdj f-g between the driving end and the target object, calculated according to the Pythagorean theorem.

[0022] Preferably, the fluctuation rate Bdl calculation process is as follows:

[0023]

[0024] In the formula, μ represents the average pressure of the mechanical arm driving end, The fluctuation rate of the pressure change of the driving end of the mechanical arm is calculated according to the standard deviation formula.

[0025] Preferably, in the identified area Smj, the number of target objects with a circular cross-sectional shape A is greater than the number of target objects with a square cross-sectional shape B, and the number of target objects with a triangular cross-sectional shape C, the grasping level of the target objects with a triangular cross-sectional shape is higher than that of the target objects with a square cross-sectional shape, and the grasping level of the target objects with a square cross-sectional shape is higher than that of the target objects with a circular cross-sectional shape, when the number of different types of target objects in the identified area Smj is the same, the grasping level is arranged according to the total area of the target objects, and if the total area of a single type of target object is less than that of other types of target objects, the grasping level of the corresponding type of target object is the highest.

[0026] Preferably, the driving management unit arranges the cross-sectional contact points from short to long according to the driving distance Qdj, and controls the mechanical arm to preferentially select the cross-sectional contact point with the shortest driving distance Qdj to grasp the target object.

[0027] Preferably, when the fluctuation rate Bdl is higher than the fluctuation threshold BDY, it indicates that the pressure change of the driving end of the mechanical arm is abnormal, and it is suggested to check the abnormal situation in time.

[0028] Compared with the prior art, the intelligent driving system of the intelligent industrial mechanical arm has the following beneficial effects:

[0029] 1、The three-dimensional coordinate system Z is established by the data acquisition module with the fixed end as the origin, which is convenient for accurate positioning and path optimization, the data acquisition module is composed of a scanning data unit, a driving data unit and a sensing data unit, the scanning data unit collects a target data set by connecting an infrared camera through a network, the driving data unit collects a driving data set according to the three-dimensional coordinate system Z, the sensing data unit collects a sensing data set by connecting a sensing device through a network, the intelligent driving module classifies target objects according to cross-sectional shapes according to the target data set, and generates corresponding identified areas Smj, through real-time data updating, the intelligent driving module quickly adapts to a dynamic sorting scene, the intelligent driving module analyzes and generates driving distances Qdj between driving ends and target objects according to the driving data unit, the continuity of the moving path is optimized, frequent start-stop or overload operation of the mechanical arm is avoided, the service life of the equipment is prolonged, the intelligent driving module analyzes the pressure change degree of the driving end of the mechanical arm according to the sensing data set, and generates corresponding fluctuation rates Bdl, target object sliding is avoided, and the accuracy of multi-dimensional collaborative control is high.

[0030] 2、The application sets a fixed range fluctuation threshold BDY through the intelligent driving module, and then combines the recognition area Smj, the driving distance Qdj and the fluctuation rate Bdl to evaluate the grabbing level of different types of target objects, select the optimal cross-section contact point, monitor the grabbing state of the driving end of the mechanical arm, and identify the number of target objects in the recognition area Smj, A of the target objects with a circular cross-section > B of the target objects with a square cross-section > C of the target objects with a triangular cross-section, the grabbing level of the triangular cross-section target objects is higher than that of the square cross-section target objects, and the grabbing level of the square cross-section target objects is higher than that of the circular cross-section target objects, when the number of different types of target objects in the recognition area Smj is the same, the grabbing level will be arranged according to the total area of the target objects, if the total area of a single type of target object is smaller than that of other types of target objects, the grabbing level of the corresponding type of target object is the highest, this judgment logic ensures that the system can quickly select the optimal grabbing target in a complex scene, and significantly improves the sorting efficiency, the driving management unit arranges the cross-section contact points from short to long according to the driving distance Qdj, and controls the mechanical arm to preferentially select the cross-section contact point with the shortest driving distance Qdj to grab the target object, thereby shortening the moving path of the mechanical arm, reducing energy consumption and time cost, and improving the safety and efficient driving production efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 The system flowchart of the application. DETAILED DESCRIPTION

[0032] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.

[0033] Since the traditional intelligent driving system of industrial mechanical arm has poor environmental adaptability, it is difficult to adapt to dynamic sorting scenes in real time, the motion trajectory has deviation, the sorting efficiency and accuracy are low, in addition, in the process of grabbing target objects by the mechanical arm, it is difficult to find problems such as missing grabbing and falling in time, therefore, an intelligent driving system of intelligent industrial mechanical arm is provided, please refer to Figure 1 An intelligent driving system of intelligent industrial mechanical arm, comprising a mechanical arm, a data acquisition module and an intelligent driving module.

[0034] The mechanical arm comprises a fixed end, a large arm, a joint movable end, a small arm and a driving end, the fixed end is used for fixedly mounting the mechanical arm, the joint movable end is used for driving the large arm and the small arm, and the driving end is provided with a grabbing clamp for grabbing a target object;

[0035] The data acquisition module establishes a three-dimensional coordinate system Z with the fixed end as the origin, so as to facilitate accurate positioning and path optimization. The data acquisition module comprises a scanning data unit, a driving data unit and a sensing data unit. The scanning data unit collects a target data set by connecting an infrared camera through a network. The target data set comprises scanning data of the target object. The expression of the target data set is {M1, M2, M3,..., Mn}. M1 to Mn represent the scanning data of the first to the nth target object. The scanning data comprises a cross-sectional shape and a cross-sectional size, so as to facilitate automatic classification of objects with different shapes.

[0036] The driving data unit collects a driving data set according to the three-dimensional coordinate system Z. The driving data set comprises coordinate data of all nodes. The expression of the driving data set is {J1, J2, J3,..., Je}. J1 to Je represent the coordinate data of the first to the e-th node. The nodes comprise a moving point of the driving end and a cross-sectional contact point of the target object, so as to ensure the accuracy of spatial positioning.

[0037] The sensing data unit collects a sensing data set by connecting a sensing device through a network. The sensing data set comprises pressure data of the driving end of the mechanical arm. The expression of the sensing data set is {Y1, Y2, Y3,..., Yv}. Y1 to Yv represent pressure values at the first to the v-th time point.

[0038] The intelligent driving module comprises a target recognition unit, a distance evaluation unit, a pressure monitoring unit and a driving management unit. The target recognition unit classifies the target object according to the cross-sectional shape according to the target data set, and generates a corresponding recognition area Smj. The calculation process is as follows:

[0039] The target object is classified according to the cross-sectional shape according to the target data set. The target object with a circular cross-sectional shape is a class A target object, and the target object with a square cross-sectional shape is a class B target object.

[0040]

[0041] In the formula, r a represents the cross-sectional radius of the a-th target object, the cross-sectional shape of the a-th target object is circular, A represents the number of target objects with a circular cross-sectional shape, represents the total area of all target objects with a circular cross-sectional shape, l b represents the cross-sectional length of the b-th target object, k b represents the cross-sectional width of the b-th target object, the cross-sectional shape of the b-th target object is square, and B represents the number of target objects with a square cross-sectional shape. represents the total area of all objects with square cross-sectional shapes, s c represents the cross-sectional side length of the cth object, h c represents the height of the cth object in the cross-section perpendicular to s c represents the cross-sectional shape of the cth object is a triangle, C represents the number of objects with triangular cross-sectional shapes, represents the total area of all objects with triangular cross-sectional shapes, through real-time data updating, quickly adapt to dynamic sorting scene;

[0042] The distance evaluation unit analyzes the driving distance Qdj between the driving end and the object according to the driving data unit, and the calculation process is as follows:

[0043] According to the driving data set, the coordinates of the fth moving point are marked as Jf(x f ,y f ,z f ), and the coordinates of the gth cross-sectional contact point are marked as Jg(x g ,y g ,z g );

[0044]

[0045] In the formula, represents the straight-line distance from the fth moving point to the gth cross-sectional contact point, which is calculated according to the Pythagorean theorem, that is, the driving distance Qdj between the driving end and the object f-g , the continuity of the moving path is optimized, avoiding frequent start-stop or overload operation of the mechanical arm, prolonging the service life of the equipment;

[0046] The pressure monitoring unit analyzes the pressure change degree of the mechanical arm driving end according to the sensing data set, and generates the corresponding fluctuation rate Bdl, and the calculation process is as follows:

[0047]

[0048] In the formula, μ represents the average pressure of the mechanical arm driving end, represents the fluctuation rate of the pressure change of the mechanical arm driving end, which is calculated according to the standard deviation formula, applied to the moving stage in the grabbing process, avoiding the target object from slipping, and the multi-dimensional collaborative control has high precision;

[0049] The driving management unit sets a fixed range of fluctuation threshold BDY, and combines the identified area Smj, driving distance Qdj and fluctuation rate Bdl to evaluate the grabbing level of different kinds of objects, select the optimal cross-sectional contact point, monitor the grabbing state of the mechanical arm driving end, and generate the corresponding driving suggestion;

[0050] When the number of objects with a circular cross-sectional shape A is greater than the number of objects with a square cross-sectional shape B, which is greater than the number of objects with a triangular cross-sectional shape C in the identified area Smj, the grasping level of objects with a triangular cross-sectional shape is higher than that of objects with a square cross-sectional shape, and the grasping level of objects with a square cross-sectional shape is higher than that of objects with a circular cross-sectional shape. When the number of different types of objects in the identified area Smj is the same, the grasping level is arranged according to the total area of the objects. If the total area of a single type of object is less than that of other types of objects, the grasping level of the corresponding type of object is the highest. This judgment logic ensures that the system quickly selects the optimal grasping target in a complex scene, significantly improves sorting efficiency, and drives the management unit to arrange the cross-sectional contact points from short to long according to the driving distance Qdj, and controls the robot arm to preferentially select the cross-sectional contact point with the shortest driving distance Qdj to grasp the target object, shortens the movement path of the robot arm, reduces energy consumption and time cost, and the fluctuation rate Bdl is higher than the fluctuation threshold BDY, indicating that the pressure change at the driving end of the robot arm is abnormal, and it is recommended to check the grasping abnormality in time. Real-time pressure monitoring and timely warning can avoid equipment damage or sorting errors, improve safety, and improve production efficiency.

[0051] Example 1

[0052] In this experiment, the robot arm with driving end coordinates (1, 2, 3) was selected as the experimental object. After scanning, the coordinates of the target object cross-sectional contact point were (4, 6, 8). The driving distance Qdj between the driving end of the robot arm and the target object was calculated as follows:

[0053]

[0054] In the formula, according to the Pythagorean theorem, the straight-line distance from the moving point of the driving end to the cross-sectional contact point of the target object is about 7.07. The driving distance Qdj between the driving end of the robot arm and the target object is about 7.07. f-g about 7.07.

[0055] Example 2

[0056] In this experiment, a robot arm used for sorting tubular objects was selected as the experimental object. After detection, the pressure values of the driving end of the robot arm within 5 minutes were 10 Pa, 12 Pa, 15 Pa, 11 Pa, and 13 Pa. The fluctuation rate Bdl of the pressure change of the driving end of the robot arm was calculated as follows:

[0057]

[0058] In the formula, μ=12.2 Pa represents the average pressure of the driving end of the mechanical arm, according to the standard deviation formula, the fluctuation rate of the pressure change of the driving end of the mechanical arm is calculated as 2.96, the fluctuation threshold BDY is set as 3.5-9.8, it is judged that 2.96 is lower than the fluctuation threshold BDY, the pressure change of the driving end of the mechanical arm is normal, and it is not necessary to check the abnormal situation of grabbing.

[0059] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are only by way of example and that modifications, changes, substitutions and alterations can be made thereto without departing from the spirit and scope of the application as defined in the following claims, in which:

Claims

1. An intelligent drive system for an intelligent industrial robot arm, characterized by: The mechanical arm, the data acquisition module and the intelligent driving module are included. The mechanical arm includes a fixed end, a large arm, a joint movable end, a small arm and a driving end, the fixed end is used for fixing and installing the mechanical arm, the joint movable end is used for driving the large arm and the small arm, and the driving end is provided with a grabbing clamp for grabbing a target object. The data acquisition module establishes a three-dimensional coordinate system with a fixed end as the origin , the data acquisition module is composed of a scanning data unit, a driving data unit and a sensing data unit, the scanning data unit collects a target data set through a network connection infrared camera, the target data set includes scanning data of a target object, the driving data unit collects a driving data set according to the three-dimensional coordinate system , the driving data set includes coordinate data of all nodes, the sensing data unit collects a sensing data set through a network connection sensing device, and the sensing data set includes pressure data of the driving end of the mechanical arm The intelligent driving module is composed of a target recognition unit, a distance evaluation unit, a pressure monitoring unit and a driving management unit, the target recognition unit classifies target objects according to cross-sectional shapes according to a target data set, and generates corresponding recognition areas , the distance evaluation unit analyzes the driving distance between the driving end and the target object according to the driving data unit , the pressure monitoring unit analyzes the pressure change degree of the driving end of the mechanical arm according to the sensing data set, and generates the corresponding fluctuation rate , the driving management unit is provided with a fixed range of fluctuation threshold , combined with the recognition area , the driving distance and the fluctuation rate , the grasping level of different kinds of target objects is evaluated, the optimal cross-sectional contact point is selected, the grasping state of the driving end of the mechanical arm is monitored, and the corresponding driving suggestion is generated; The identified area Among them, the number of target objects with a circular cross-sectional shape The number of target objects with a square cross-sectional shape The number of target objects with a triangular cross-sectional shape When the number of target objects with a triangular cross-sectional shape is greater than the number of target objects with a square cross-sectional shape, and the number of target objects with a square cross-sectional shape is greater than the number of target objects with a circular cross-sectional shape, the grasping level of the target objects with a triangular cross-sectional shape is higher than that of the target objects with a square cross-sectional shape, and the grasping level of the target objects with a square cross-sectional shape is higher than that of the target objects with a circular cross-sectional shape, the identified area Among them, when the number of different kinds of target objects is the same, the grasping level is arranged according to the total area of the target objects, and if the total area of a single kind of target object is less than the total area of other kinds of target objects, the grasping level of the corresponding kind of target object is the highest.

2. The intelligent driving system of an intelligent industrial robot arm according to claim 1, characterized in that: The expression of the target data set is , to indicates the scanning data of the first to the target objects, and the scanning data includes cross-sectional shape and cross-sectional size.

3. The intelligent driving system of an intelligent industrial robot arm according to claim 2, characterized in that: The expression of the driving data set is , to represent the coordinate data of the first to the node, including the moving point of the driving end and the cross-sectional contact point of the target object.

4. The intelligent driving system of an intelligent industrial robot arm according to claim 3, characterized in that: The expression of the sensor data set is , to denotes the pressure value from the first time point to the time point.

5. The intelligent drive system of an intelligent industrial robot arm according to claim 4, characterized in that: The recognition area The calculation process is as follows: according to the target data set, the targets are classified according to the cross-sectional shape, wherein the targets with a circular cross-sectional shape are Class targets, the targets with a square cross-sectional shape are Class targets, In the formula, represents the cross-sectional radius of the th target object, the cross-sectional shape of the th target object is circular, represents the number of target objects with a circular cross-sectional shape, represents the total area of all target objects with a circular cross-sectional shape, represents the cross-sectional length of the th target object, represents the cross-sectional width of the th target object, the cross-sectional shape of the th target object is square, represents the number of target objects with a square cross-sectional shape, represents the total area of all target objects with a square cross-sectional shape, represents the cross-sectional side length of the th target object, represents the height of the th target object cross section perpendicular to , the cross-sectional shape of the th target object is triangular, represents the number of target objects with a triangular cross-sectional shape, represents the total area of all target objects with a triangular cross-sectional shape.

6. The intelligent drive system of an intelligent industrial robot arm according to claim 5, wherein: The driving distance The calculation proceeds as follows: According to the driving data set, the coordinates of the first moving point are recorded as , and the coordinates of the first cross-section contact point are recorded as ; In the formula, represents the straight-line distance from the first moving point to the first cross-section contact point, i.e., the driving distance between the driving end and the target object .​​ 7. The intelligent drive system of an intelligent industrial robot arm according to claim 6, characterized in that: The volatility The calculation proceeds as follows: In the formula, represents the average pressure of the driving end of the robot arm, represents the fluctuation rate of the driving end pressure change of the robot arm calculated according to the standard deviation formula.

8. The intelligent drive system of an intelligent industrial robot arm according to claim 1, wherein: The driving management unit drives the robot arm according to the driving distance The cross-sectional contact points are arranged from short to long, and the robot arm is controlled to preferentially select the driving distance The shortest cross-sectional contact point grasps the target object.

9. The intelligent drive system of an intelligent industrial robot arm according to claim 8, characterized in that: The volatility Above the volatility threshold At this time, the pressure change of the driving end of the mechanical arm is abnormal, and timely inspection of the abnormal situation of grabbing is suggested.

Images