MODELING AND OPTIMIZATION OF REFLOW THERMAL PROFILING OPERATION: A COMPARATIVE STUDY

In this study, a comparative study of optimizing the reflow thermal profiling parameters using a hybrid artificial intelligence and the desirability function approaches without/with combining multiple performance characteristics into a single desirability is presented. Reflow soldering is the key determinant for the improvement of the first-pass yields of electronics assembly. A reflow thermal profile is a time-temperature contour with multiple performance characteristics utilized to monitor the heating effects on a printed circuit board (PCB) and surface mount components (SMCs) in the reflow oven. The use of an inadequate reflow thermal profile may not only produce a variety of soldering failures, but can also result in the needs for considerable reworking and waste. An L-18 (2(1)x3(7)) Taguchi experiment design is conducted to collect the thermal profiling data. A quick propagation (QP) neural network is modeled based on experimental data to formulate the nonlinear relationship between the thermal profiling factors and responses, and a genetic algorithm (GA) is used in the optimization of thermal profiling factors with the fitness function based on the trained QP neural network model. Alternatively, the response columns for the experimental data can be transformed into a single measure of desirability which is then optimized by the desirability function approach with the response weightings derived from an analytic hierarchy process (AHP). The empirical evaluation results show that the desirability function approach with combining the multiple performance into a single desirability delivery superior soldering performance to that obtained by the hybrid artificial intelligence method without combining the multiple performance into a single desirability, as measured by the DPMO, yield rate, and process sigma.