Modeling and optimization of laser direct structuring process using artificial neural network and response surface methodology

• Main Authors: Bassim Bachy, Jörg Franke
• Format: Article
• Language: English
• Published: Growing Science 2015-09-01
• Series: International Journal of Industrial Engineering Computations
• Subjects: LDS process; MID process; Modeling; Artificial neural network; Response surface methodology
• Online Access: http://www.growingscience.com/ijiec/Vol6/IJIEC_2015_14.pdf

Laser direct structuring (LDS) is very important step in the MID process and it is a complex process due to different parameters, which influence on this process and its final product. Therefore, it is very important to use a reliable model to predict, analyze and control the performance of the (LDS) process and the quality of the final product. In this work we develop mathematical models by using Artificial Neural Network (ANN) and Response Surface Methodology (RSM) to study this process. The proposed models are used to study the effect of the LDS parameters on the groove dimensions (width and depth), lap dimensions (groove lap width and height) and finally the heat effective zone (interaction width), which are important to determine the line width/space in the MID products and the metallization profile after the metallization step. We also study the relationship between the LDS parameters and the surface roughness which is very important factor for the adhesion strength of MID structures. Moreover these models capable of finding a set of optimum LDS parameters that provide the required micro-channel dimensions with the best or the suitable surface roughness. A set of experimental tests are carried out to validate the developed ANN and the RSM models. It has been found that the predicted values for the proposal ANN and RSM models were closer to the experimental values, and the overall average absolute percentage errors were 4.02 % and 6.52%, respectively. Finally, it has been found that, the developed ANN model could be used to predict the response of the LDS process more accurately than RSM model.