An Analysis of Competitive Associative Net for Temperature Control of RCA Cleaning Solutions
This paper illustrates and analyzes the competitive associative net called CANS applied to modelswitching control of the temperature of RCA cleaning solutions, where the RCA clean is the industry standard way to clean silicon wafers and the temperature control is important for a stable cleaning performance. Since the control is difficult owing that the RCA cleaning solutions expose exothermic chemical reactions being nonlinear and time-varying, we have presented an architecture of model-sivitching predictive controller (MSPC) using CAN2, so far. Here, we analyze the behavior of the MSPC in detail and show the advantages of the architecture, such as the model-switching scheme compensating slow learning speed, the incremental learning ability of the CAN2, etc. by means of computer simulation.
S. Kurogi H. Nobutomo T. Nishida H. Sakamoto Y. Fuchikawa M. Mimata K. Itoh
Kyushu Institute of Technology, Kitakyushu 804-8550, Japan Komatsu Electronics Inc., Hiratsuka 254-8543, Japan
国际会议
8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)
上海
英文
995-1000
2001-11-14（万方平台首次上网日期，不代表论文的发表时间）