Optimization of chrome plating process design: A neural network approach

The cost-effective optimisation of any engineering operation involves either the minimization or maximization of an objective function. hi most cases the significant variables are subject to constraints such as valid ranges (max and min limits) as well as those that arise from the process model equations. In the case of electroplating optimization, both the objective function and the constraints are non-linear. Computational methods of non-linear programming with constraints usually have to cope with problems such as numerical evaluation of derivatives and feasibility issues. The aim of this paper is to propose an innovative optimization method based on the neural network, viz. model equations used in the conventional optimization methods are replaced by an equivalent trained neural network and then a neural network search was performed on the region of interest. It was found that through the proposed approach mapping of the objective function in full allows multiple optima to be found more easily. Moreover, the constraints can be dealt with easily afterwards since points with violated constraints can be recognized and classified. An illustration of this approach was applied in an electroplating process - chrome plating of marine engine piston crown with the objective to achieve quality deposition in the ring grooves of the piston crown.