Abstract

Surface modification is an effective method to improve the electrochemical property of hydrogen storage alloy. In order to investigate the influence of process factors of electroless copper (Cu) plating for AB₅-type hydrogen storage alloy on Cu coating mass, a novel modeling approach, support vector regression (SVR) combined with particle swarm optimization (PSO), was proposed to construct a mathematical model for prediction of the mass changes of Cu coating over the AB₅ hydrogen storage alloy surface based on three factors, including temperature, pH value and Ni²⁺ concentration. The modeling accuracy and reliability of the created SVR model are validated through leave-one-out cross validation (LOOCV), and compared with those of a second-order polynomial model. The results show that the predicted errors by SVR-LOOCV models are all smaller than those achieved by the second-order polynomial model. The SVR model is further applied to predict the process parameters for the maximum Cu coating mass. These studies suggest that SVR can be used as an effective methodology to assist the design of experiment, and is helpful to precisely control the coating mass via fine adjustment of the process parameters.

Key words: Surface modification, electroless copper plating, hydrogen storage alloy, support vector regression, modeling and prediction.