Rolling force prediction method based on quantum particle swarm optimization and BP neural network
The invention discloses a rolling force prediction method based on a quantum particle swarm algorithm and a BP neural network, and the method comprises the following steps: 1, collecting sample data, including an inlet thickness, a rolling reduction, a rolling speed, a rolling temperature, a rolled...
Saved in:
Main Authors | , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
23.06.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention discloses a rolling force prediction method based on a quantum particle swarm algorithm and a BP neural network, and the method comprises the following steps: 1, collecting sample data, including an inlet thickness, a rolling reduction, a rolling speed, a rolling temperature, a rolled piece width, a roller radius, a conventional model prediction value, a self-learning coefficient, and a rolling force measured value; 2, screening data in the samples; 3, normalizing data in the samples, and dividing the collected original production data samples of the strip steel into a training set, a verification set and a test set; 4, the network structure of the BP neural network is determined, and it is determined that input nodes of the neural network are the rolled piece inlet thickness, the rolling reduction, the rolling speed, the rolling temperature, the rolled piece width, the roller radius and a traditional model forecast value; training the BP neural network by using the training set, the verificatio |
---|---|
Bibliography: | Application Number: CN202310008543 |