Roll Bending Arc Torque Control for Smooth Variable Curvature Forming
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The forming radius of variable curvature roll bending profiles is difficult to control, leading to the inability to achieve smooth transitions between profiles with different curvatures, especially in large-size and asymmetric section parts, and current equipment lacks effective solutions for efficient and precise control.
Innovation Solution
A variable curvature bending arc control method for roll bending machines using a combination of genetic algorithm, back propagation neural network, and particle swarm optimization to accurately control the bending arc torque, involving data collection, neural network parameter optimization, and iterative learning processes to stabilize control under complex conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional manual control methods are used for roll bending machines, then operational simplicity is maintained, but manufacturing precision and productivity deteriorate due to repeated forming operations and inability to achieve smooth curvature transitions
Solution Approach 1:
The patent replaces manual mechanical control with an automated control system comprising a neural network controller and genetic algorithm optimizer. This substitution enables precise control of bending radius and smooth curvature transitions that cannot be achieved through manual operation, directly resolving the contradiction between precision and operational simplicity.
Solution Approach 2:
The patent dynamically adjusts control parameters (bending torque, roller positions, feed rate) based on real-time feedback and neural network predictions. This parameter optimization enables precise forming radius control and smooth curvature transitions while maintaining system adaptability, addressing the precision-precision tradeoff.
2Manufacturing precision
If repeated forming operations are performed to satisfy shape requirements, then manufacturing precision can be improved, but productivity deteriorates due to increased processing time and operational complexity
Solution Approach 1:
The patent performs preliminary calculations and predictions using the neural network model before actual forming operations. By pre-determining optimal bending torque and roller positions, the system achieves high precision in a single pass without requiring repeated adjustments, thereby improving both precision and productivity simultaneously.
Solution Approach 2:
The patent implements a closed-loop feedback control system that continuously monitors forming process parameters and adjusts control outputs in real-time. This feedback mechanism ensures high profile accuracy while minimizing the need for repeated operations, resolving the contradiction between precision and efficiency.
3Adaptability or versatility
If variable curvature profile processing is attempted with current technology, then adaptability is improved, but manufacturing precision deteriorates due to inability to achieve smooth transitions between different curvatures
Solution Approach 1:
The patent employs a dynamic control system that continuously adapts bending parameters based on the desired curvature profile. The neural network controller dynamically adjusts roller positions and bending torque in real-time, enabling smooth transitions between different curvatures while maintaining high precision, thus resolving the adaptability-precision contradiction.
Data Source
AI summary
A variable curvature bending arc control method for a roll bending machine includes specific steps as follows: collecting and pre-processing data; initializing the network structure, and determining the parameters such as a number of input layer nodes, hidden layer nodes and output layer nodes and other parameters of the back propagation neural network according to the learning sample data; encoding a weight value and a threshold value of a back propagation neural network into individuals in a population according to set coding rules, and initializing the population according to a set population size and a random initialization method; GA-PSO iterative operation; initializing the back propagation neural network parameter; training the back propagation neural network; and an application of the control model. The control method accurately controls the variable curvature bending arc torque for the roll bending machine by combining genetic algorithm, back propagation neural network and particle swarm optimization.