Unlock instant, AI-driven research and patent intelligence for your innovation.

Neural network adaptive control method of non-contact type suspension grabbing system

An adaptive control and neural network technology, applied in the field of non-contact magnetic levitation transmission, can solve problems such as falling objects, excessive wind resistance, and affecting the stability of the grasped object, achieving low power consumption, low noise, and improving two degrees of freedom Effect of gripping and handling performance

Pending Publication Date: 2021-06-18
QUFU NORMAL UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the non-contact magnetic levitation grasping system is essentially a nonlinear and unstable system, and it works in two-dimensional horizontal and axial movements. Especially in order to improve production efficiency, the handling speed changes relatively quickly, and the wind resistance inevitably caused by high-speed movement Objects vibrate horizontally, offset directly below the winding, and the wind resistance is too large, which may even cause the object to fall, which affects the stability of the grasped object. Therefore, it is necessary to set up a non-contact suspension grasping control system with robust performance and superior performance. Many scientific research Workers have successively carried out research on self-adaptation and sliding mode control based on the magnetic suspension platform, and have realized the precise control of the magnetic suspension position to a certain extent, but have not done much research on the control of the two-degree-of-freedom magnetic suspension grasping system , which poses a profound challenge to the work of the non-contact suspension grasping system

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
  • Neural network adaptive control method of non-contact type suspension grabbing system
  • Neural network adaptive control method of non-contact type suspension grabbing system
  • Neural network adaptive control method of non-contact type suspension grabbing system

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0158] Example 1, the simulation experiment of the optimal setting of the grasping height during the handling process, such as image 3 , Figure 4 and Figure 5 As shown, after the object to be grasped is suspended stably, it is transported horizontally at a speed of 25.1cm / s at t=0.5s. Increased to 4.53×10-5mm, after one oscillation cycle, the gripping height optimization setting of formula (7) reduces the axial gripping height to 8mm, and its gripping height optimization performance is shown in Table 2, and the gripping height is stable The time is 0.15s, the initial horizontal oscillation range of the axial air gap is 2.86×10-5mm, and the oscillation range increases to 4.53×10-5mm after increasing the speed. After the suspension height is optimized and set, the present invention returns to the initial oscillation range under the control , which proves that the control of the present invention has a strong ability to adapt to changes in working conditions and dynamic perf...

example 2

[0161] Example 2, the simulation experiment of axial grasping and rising, such as Figure 6 , Figure 7 and Figure 8 As shown, the suspension grabbing height is set to 14mm, the suspension grabbing is started at t=0s, and the wind resistance in the rapid ascent process is simulated at t=5s, and the axial resistance of 0.9sin[9(t-5)]N is applied to carry out the The comparison results of axial air gap tracking under PID control and the axial air gap tracking of the present invention are shown in Table 3. No matter in terms of grasping height change, recovery time, air gap oscillation range and stabilization time, the control effect of the present invention is Obviously better than PID control.

[0162] Table 3 Axial interference force application performance comparison

[0163]

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 discloses a neural network adaptive control method for a non-contact type suspension grabbing system, and the method comprises the steps: constructing a non-contact type suspension grabbing two-degree-of-freedom motion model, and enabling the interference under the two-degree-of-freedom model to be attributed to a single degree of freedom, so as to achieve the active and passive axial horizontal air gap control; aiming at the problem of horizontal oscillation in the carrying process in the working process of the non-contact type suspension grabbing system, providing a safety stability domain and grabbing height optimization setting scheme; designing a neural network self-adaptive controller of the non-contact type suspension grabbing system by combining a state observer and model reference self-adaption, selecting a strictly linear interference-free suspension grabbing expectation model, and achieving an optimal neural network auxiliary input signal through neural network weight online adjustment; and approaching the non-contact suspension grabbing system completely an expected model. According to the invention, the working performance of the non-contact suspension grabbing system and the capability of suppressing wind resistance interference are greatly improved while the stability of the system is ensured.

Description

technical field [0001] The invention relates to a neural network self-adaptive control method for a non-contact suspension grabbing system, in particular to a non-polluting, non-contact grabbing and handling working process control applied to conductors and high magnetic permeability objects, belonging to Non-contact magnetic levitation transmission field. Background technique [0002] The robot arm operates by intelligently simulating human hands, which can replace humans in harmful and dangerous environments; its precise and reliable movements, rapid response, and high rigidity greatly improve production efficiency. However, traditional robotic arms directly touch, Grabbing objects can easily cause deformation, damage and pollution of objects, and grasping at high temperatures can even cause damage to the gripper of the machine. For this reason, the New Energy Laboratory proposed a non-contact magnetic levitation grabbing system. This suspension grabbing system combines ...

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
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 褚晓广宋蕊孔英王伟超
Owner QUFU NORMAL UNIV