Development of adaptive nonlinear regression methods for stable and efficient process control

2014 Fiscal Year Final Research Report

• Project/Area Number: 24760629
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Reaction engineering/Process system
• Research Institution: The University of Tokyo
• Principal Investigator: KANEKO Hiromasa 東京大学, 工学(系)研究科(研究院), 助教 (00625171)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: プロセス管理 / ソフトセンサー / モデルの劣化 / 適応型モデル / サポートベクター回帰 / アンサンブル学習 / ベイズの定理 / 予測誤差

Outline of Final Research Achievements

A soft sensor predicts the values of some process variable y that is difficult to measure. To maintain the predictive ability of a soft sensor model, adaptation mechanisms are applied to soft sensors. However, even these adaptive soft sensors cannot predict the y-values of various process states in chemical plants, and it is difficult to ensure the predictive ability of such models on a long-term basis. Therefore, we propose a method that combines online support vector regression (OSVR) with an ensemble learning system to adapt to nonlinear and time-varying changes in process characteristics and various process states in a plant. Several OSVR models, each of which has an adaptation mechanism and is updated with new data, predict y-values. A final predicted y-value is calculated based on those predicted y-values and Bayes’ rule. We analyzed simulation datasets and real industrial datasets, and demonstrate the superiority of the proposed method.

Free Research Field

プロセスシステム工学、プロセス制御、計量化学、化学情報学