A self-adaptive variant pso-bp neural network strip crown prediction method
A PSO-BP, BP neural network technology, applied in the direction of contour control, etc., can solve the problems that BP neural network is easy to fall into local minimum convergence speed, SVM algorithm is difficult to implement multi-classification problems, and difficult to achieve modeling difficulty , short cycle, and the effect of improving accuracy
Active Publication Date: 2020-04-10
UNIV OF SCI & TECH BEIJING
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The above machine learning models are all simple models, and there are big problems in the model, such as BP neural network is easy to fall into local minimum and the convergence speed is slow, SVM algorithm is difficult to install large-scale training samples and has difficulties in solving multi-classification problems, etc.
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 1
[0037] The present embodiment provides a PSO-BP neural network strip crown prediction method that introduces adaptive variation, the method includes: initializing the topology of the BP neural network, determining the number of neurons in the input layer, hidden layer, and output layer , select the activation function of neural network; Select the factor that influences strip convexity as the input of described input layer, with the output of described output layer as the output of described output layer with the strip convexity at rack outlet;
[0038]Initialize the weights and thresholds of the BP neural network, encode the initialized weights and thresholds into particles, set the basic parameters of the PSO algorithm, optimize the BP neural network with the PSO algorithm, and introduce adaptive variation into the PSO-BP neural network model A PSO-BP neural network with self-adaptive variation is constructed, and the PSO-BP neural network with self-adaptive variation can be ...
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 mainly belongs to the technical field of strip steel plate shape control, and particularly relates to a PSO-BP neural network strip steel convexity predicting method introducing self-adaptation variation. According to the predicating method, real-time correction is conducted on a plate shape predicting model through actual data, and the actual situation of constant rolling mill plateshape model changes is achieved; an accurate model of the rolling process does not need to be established, only accurate input and output are needed, the self-adaptation variation is used for the PSO-BP algorithm through correction of the prediction algorithm and control parameters, then, involving in local minimum is prevented, accurate strip steel convexity prediction can be achieved, the rolling field requirement is met, plate shape prediction is more accurately conducted, and accordingly the plate shape control precision is improved.
Description
technical field [0001] The invention mainly belongs to the technical field of strip steel shape control, and in particular relates to an adaptive variation PSO-BP neural network strip convexity prediction method. Background technique [0002] The development of processing technology has higher and higher requirements for the quality standards of metal strip products, and the research on flat shape has always been the frontier and hot spot of strip steel production technology. In the flatness control system, the flatness production parameters will directly affect the quality and production efficiency of strip steel products, so the research on flatness control technology plays a vital role in improving the core competitiveness of iron and steel enterprises. [0003] In recent years, researchers at home and abroad have carried out in-depth research on how to further improve the quality of flatness control. While looking for a more accurate system model, they tried to study the...
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): B21B37/28
CPCB21B37/28
Inventor 张飞朱永波张勇军肖雄王增权
Owner UNIV OF SCI & TECH BEIJING