An Improved Optimization Model to Predict the Deposition Rate and Smoothness of Ni Pulse-Reverse Electroplating Based on ANN and Experimental Results

The metallic layers are an essential part of MEMS (micro electromechanical system) devices, and their deposition process must be accurately controlled; this may lead to difficulties as there many input parameters for such a process. This research focuses on the parameters’ effects Ni pulse-reverse electroplating. A neural network was constructed characterize nickel electroforming parameters. sample training has established mapping relationship between output layer thickness surface roughness prediction in electroplating realized verified by experimental tests with test error 3.3%. Then, effect direct reverse current density, time, structure width, stirring speed investigated. Finally, novel 4D diagram been developed derive optimal values density relative thickness, roughness, time. can help researchers industries find suitable achieve desired deposited layer’s properties.