Optimization of Copper Electroforming Process Parameters Based on Double Hidden Layer BP Neural Network

Abstract

In order to optimize the pulse electroforming copper process, a double hidden layer BP (back propagation) neural network was constructed. Through sample training, the mapping relationship between electroforming copper process conditions and target properties was accurately established, and the prediction of microhardness and tensile strength of the electroforming layer in the pulse electroforming copper process was realized. The predicted results were verified by electrodeposition copper test in copper pyrophosphate solution system with pulse power supply. The results show that the microhardness and tensile strength of copper layer predicted by “3-4-3-2” structure double hidden layer neural network are very close to the experimental values, and the relative error is less than 2.82%. In the parameter range, the microhardness of copper layer is between 100.3~205.6 MPa and the tensile strength is between 165~485 MPa. When the microhardness and tensile strength are optimal, the corresponding range of optimal parameters are as follows: current density is 2–3 A·dm−2, pulse frequency is 1.5–2 kHz and pulse duty cycle is 10–20%.

Keywords

• double hidden layer
• BP neural network
• electroforming
• optimization