Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method and system for automatically controlling feeding

A technology of automatic control and control instructions, which is applied in neural learning methods, image data processing, biological neural network models, etc., can solve problems such as failure to meet industrial needs, damage to the surface of the target, and falling of the target, so as to improve operation Efficiency, implementation of updates, and reduction of operating process effects

Inactive Publication Date: 2021-12-07
南京付联微网络科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, by setting the operation method of fixing the grasping frequency, the grasping process of the mechanical grasping process is often inaccurate due to the deviation of the position of the target object, resulting in problems such as falling of the target object or damage to the surface of the target object.
, which cannot meet the actual industrial needs

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system for automatically controlling feeding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] In the industrial operation environment, because the high-risk environment often increases the difficulty of the operation and even endangers the health of the public, therefore, the automatic mechanical gripper that completes the expected operation tasks through programming has emerged as the times require. By replacing manual operations, it not only reduces labor The cost is invested to ensure the safety of workers, and at the same time, the automated mechanical operation also greatly improves the operating efficiency, thereby improving economic benefits. However, by setting the operation method of fixing the grasping frequency, the grasping process of the mechanical grasping process is often inaccurate due to the deviation of the position of the target object, resulting in problems such as falling of the target object or damage to the surface of the target object. , which cannot meet the actual industrial demand. Therefore, this embodiment proposes a method for autom...

Embodiment 2

[0047] In a further embodiment based on the first embodiment, the existing technology often adopts the way of preset mechanical gripper movement path to grasp the target in the process of grasping, but with the position of the target on the conveyor belt Offset, and the placement state is different from the expected, which often leads to the inability of the mechanical gripper to accurately grasp the target, or the phenomenon of falling during the grasping and transportation process due to inaccurate grasping. Therefore, this embodiment adopts real-time analysis of the environmental data of the target object to obtain the actual position of the target object, and then adjusts the movement path of the gripper to increase the gripping accuracy and improve the working efficiency.

[0048] Specifically, since the position of the target on the conveyor belt is likely to be in the same state, in order to reduce a large number of repetitive and redundant analysis operations, the movem...

Embodiment 3

[0060] In a further embodiment based on the first embodiment, during the actual grabbing operation, because defective products or other non-target goods are often mixed in the transport target, in order to improve the operating efficiency of grabbing, this embodiment When performing image data analysis to obtain the actual position of the target, further identify and analyze the type of the target. When the detected item is not the expected target, the grabbing operation will not be performed, thereby improving the grabbing efficiency and reducing the quality of the later stage. check workload.

[0061] Specifically, a target recognition model is constructed to identify target types. In order to better improve the recognition efficiency of the model, after the construction is completed, it is trained by randomly constructing a data set. According to the output results and the verification set For error comparison, weight parameters are adjusted by means of backpropagation. Th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a method and a system for automatically controlling feeding. The method specifically comprises the following steps: 1, acquiring target image data through information acquisition equipment; 2, analyzing the obtained target image data; 3, generating a manipulator control instruction according to an analysis result of the target image data; 4, generating a manipulator control instruction according to the planned motion path; 5, enabling the mechanical arm to receive the generated control instruction, and completing the grabbing according to the instruction. According to the method, the spatial position of the target object is obtained by analyzing the target image data, so the grabbing instruction is generated, and the manipulator completes grabbing operation according to the received grabbing instruction. Compared with a grabbing working process with a set fixed frequency, an analysis auxiliary mode of image data is introduced, the updating of the motion path of the mechanical gripper is achieved, and therefore, the grabbing accuracy is improved, and the working efficiency in the actual working condition is maximized.

Description

technical field [0001] The invention relates to a method and system for automatic control of feeding, in particular to the technical field of automatic control. Background technique [0002] In the process of industrial production, it is necessary to add various raw materials for production operation according to specific production requirements and production characteristics. In the process of raw material transportation, due to different raw material ratios, the quality of the product will be different from the expected phenomenon, resulting in economic Losses, even serious accidents. [0003] In the prior art, in industrial production, manipulators can help people solve many difficult problems in dangerous working environments. Therefore, in the process of material grabbing and sorting, the operation mode of mechanical automation has become the mainstream choice for industrial operations. However, by setting the operation method of fixing the grasping frequency, the gras...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/70G06K9/62G06N3/04G06N3/08B65G47/90
CPCG06T7/70G06N3/04G06N3/084B65G47/905B65G47/90G06T2207/20081B65G2203/0266G06F18/2414
Inventor 毕登科朱亮
Owner 南京付联微网络科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products