Ensemble of Competitive Associative Nets for Stable Learning Performance in Temperature Control of RCA Cleaning Solutions

The RCA cleaning method is the industry standard way for cleaning silicon wafers, and the temperature control is important for a stable cleaning performance. However, the difficulty lies in the fact that the RCA solutions cause nonlinear and time-varying exothermic chemical reactions. So far, the MSPC (model switching predictive controller) using the CAN2 (competitive associative net 2) has been developed and the effectiveness has been validated. However, we have observed that the control performance, such as the settling time and the overshoot, does not always improve with the increase of the number of learning iterations for the CAN2. To solve this problem, we introduce the bagging method for the CAN2 and first-difference signals for effectively embedding the bagging method. The effectiveness and the performance of the present method are examined by means of numerical experiments.

show abstract

Ensemble of Competitive Associative Nets for Stable Learning Performance in Temperature Control of RCA Cleaning Solutions

Cited by 2 publications

References 8 publications

Model switching predictive control using bagging CAN2 and first-difference signals for temperature control of RCA cleaning solutions

Model switching predictive control using bagging CAN2 and first-difference signals for temperature control of RCA cleaning solutions

Temperature Control of RCA Cleaning Solutions via Model Switching Predictive Control Using First-difference Signals and Bagging CAN2

Contact Info

Product

Resources

About