Prediction of bending parameters and automated operation planning for sheet-metal bending orientated to graphical programming

The core of graphical programming for sheet-metal bending is operation planning based on parameter identification, which can directly determine the bending quality and efficiency. Given this, the proposed graphical programming system and method can predict the inner arc radius of bending oriented to programming demands and optimize multi-step bending operations. At first, a neural network model based on multi-layer perceptron (MLP) was established, considering the number of neurons and hidden layers. In the bending process a fitness function was defined, and the discrete particle swarm optimization (DPSO) was improved using the adaptive inertia weight and the genetic algorithm (GA). Finally, the operation planning of 10-step and 20-step bending was simulated, and bending tests were conducted on sheet-metal workpieces for verification. The results show that the algorithm's maximum positive error and minimum negative error in predicting the arc radius are 0.12 mm and - 0.16 mm, respectively. When there are 10 bending steps, the particle swarm optimization-genetic algorithm (PSO-GA) converges after only ten evolutions; when the bending steps increase to 20, the fitness value finally stabilizes at 1.31. The optimal operations of the experimental six-step bending part are 6 -> 5 -> 4 -> 3 -> 1 -> 2. This result indicates that the workpiece is turned over three times and turned around once in the sheet-metal bending process, which is consistent with the simulation, thus verifying the bending efficiency and accuracy.