Ensemble of Competitive Associative Nets for Stable Learning Performance in Temperature Control of RCA Cleaning Solutions
For cleaning silicon wafers via the RCA clean, temperature control is important in order to obtain a stable performance, but it is difficult mainly because the RCA solutions expose 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 overshoot and settling time, does not always improve as the number of learning iterations increases when using multiple units of the CAN2. So we apply the ensemble learning scheme to the CAN2 for stable control over learning iterations, and we examine the effectiveness of the present method by means of computer simulation.
KeywordsControl Performance Settling Time Asymptotic Optimality Predictive Controller Allowable Error
Unable to display preview. Download preview PDF.
- 2.Rumelhart, D.E., Zipser, D.: A feature discovery by competitive learning. In: Rumelhart, D.E., McClelland, J.L., PDP Research Group (eds.) Parallel Distributed Processing, vol. 1, pp. 151–193. The MIT Press, Cambridge (1986)Google Scholar
- 3.Kurogi, S., Nishida, T., Sakamoto, T., Itoh, K., Mimata, M.: A simplified competitive associative net and a model-switching predictive controller for temperature control of chemical solutions. In: Proc. ICONIP 2000, pp. 791–796 (2000)Google Scholar
- 4.Kurogi, S., Nishida, T., Nobutomo, H., Sakamoto, T., Mimata, M., Itoh, K.: A thermal model of the RCA cleaning system and adaptive predictive temperature control of cleaning solutions (in Japanese). Trans. SICE of JAPAN 37(8), 754–762 (2001)Google Scholar
- 5.Kurogi, S., Nobutomo, H., Sakamoto, H., Fuchikawa, Y., Mimata, M., Itoh, K.: An analysis of competitive associative net for temperature control of RCA cleaning solutions. In: Proc. ICONIP 2001, pp. 957–962 (2001)Google Scholar
- 6.Kurogi, S., Nishida, T.: Adaptive and predictive control using competitive associative net for learning and switching of multiple models (in Japanese). Trans. SICE of JAPAN 37(3), 203–212 (2001)Google Scholar
- 7.Kurogi, S.: Asymptotic optimality of competitive associative nets for their learning in function approximation. In: Proc. of the 9th International Conference on Neural Information Processing, vol. 1, pp. 507–511 (2002)Google Scholar
- 8.Kurogi, S., Araki, N., Miyamoto, H., Fuchikawa, Y., Nishida, T.: Temperature control of RCA cleaning solutions using batch learning competitive associative Net. In: Proc. SCI 2004, vol. 5, pp. 18–23 (2004)Google Scholar
- 9.Kurogi, S., Sawa, M., Ueno, T., Fuchikawa, Y.: A batch learning method for competitive associative net and its application to function approximation. In: Proc. SCI 2004, vol. 5, pp. 24–28 (2004)Google Scholar
- 10.Tomisaki, H., Kurogi, S., Araki, N., Nishida, T., Fuchikawa, Y., Mimata, M., Itoh, K.: Cross-validation of competitive associative nets for stable temperature control of RCA cleaning solutions. In: Proc. ICONIP 2005, pp. 166–170 (2005)Google Scholar
- 11.Evaluating Predictive Uncertainty Challenge: http://predict.kyb.tuebingen.mpg.de/pages/home.php
- 13.Chandrasekaran, H., Manry, M.T.: Convergent design of a piecewise linear neural network. In: Proc. IJCNN 1999, vol. 2, pp. 1339–1344 (1999)Google Scholar