Anti-sway control method for compound load position tracking based on variable structure neural network
A load location, neural network technology, applied in neural learning methods, biological neural network models, program control, etc., can solve problems such as non-adaptation, and the system is difficult to achieve results, to improve safety, improve anti-shake effect, and prevent shake effect
Active Publication Date: 2021-07-02
江阴市智行工控科技有限公司 +2
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] At present, many driving anti-sway algorithms are designed based on the precise model of the system, but for the actual system, the different states of the system may not be suitable for a set of fixed system parameters, so the system will be difficult in some working conditions achieve the desired effect
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0048] The method of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0049] Build a variable structure fuzzy neural network as a parameter corrector, such as Figure 1-2 As shown, including input layer, inference layer, rule layer and output layer:
[0050] Input layer: pass the input state quantity to the reasoning layer;
[0051] Inference layer: Gaussian function is selected as the membership function, and the Gaussian function is as follows:
[0052]
[0053] Where j=1,2,...n, k=1,2,...m, n is the number of input variables, m is the number of neurons in each membership layer, σ jk and a jk Represent the standard deviation and center of the corresponding membership function, z jk represents the output of the membership function;
[0054] Rule layer: get the activation strength of fuzzy rules through full connection:
[0055]
[0056] Among them, h=1,2,...,p, p represents the number o...
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
Login to View More Abstract
The invention discloses a compound load position tracking anti-sway control method based on a variable structure neural network, which belongs to the technical field of industrial driving. The control method uses a variable structure fuzzy neural network to build a parameter corrector and a feedback control based on compound load position tracking. The corrector corrects the parameters of the controller according to the change of the system state, and the corrected controller calculates the acceleration of driving at the next moment through the input of the system. The compound load position tracking anti-sway control method based on the variable structure neural network provided by the present invention performs anti-sway positioning on the driving, and at the same time uses the parameter corrector built by the variable structure fuzzy neural network to correct the controller parameters in real time and improve the performance of the control system. The method is simple It is easy to operate and has good robustness, so as to better improve the anti-sway effect, adapt to different working conditions during the driving process, and improve the safety and reliability of driving and carrying items.
Description
technical field [0001] The invention belongs to the technical field of industrial driving, and in particular relates to a compound load position tracking anti-sway control method based on a variable structure neural network. Background technique [0002] With the development of global industry and the expansion of production scale, the role of cranes in industrial production is increasing day by day. Cranes are an important loading and unloading equipment for heavy objects, which are widely used in various industrial sites. However, the driving will inevitably sway during the lifting process. Therefore, it is of great significance to study the control and eliminate the sway and realize the precise positioning during the hoisting of the crane to improve the working efficiency, handling accuracy and industrial control automation of the industrial site. [0003] The crane always inevitably causes the swing of the hanging object during the hoisting process. Usually, a very skil...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): B66C13/06B66C13/46B66C13/48G05B19/05G06N3/04G06N3/08
CPCB66C13/063B66C13/46B66C13/48G05B19/054G06N3/082G06N3/043
Inventor 牛丹董毅超孙长银陈夕松许翠红王思敏刘子璇
Owner 江阴市智行工控科技有限公司