期刊
CANADIAN JOURNAL OF CHEMICAL ENGINEERING
卷 101, 期 8, 页码 4587-4605出版社
WILEY
DOI: 10.1002/cjce.24822
关键词
active improvement; design of experiment; Gaussian process model; non-linear MPC
Modelling is a basic requirement for model-based controlling, monitoring, or other process strategies. This study focuses on non-linear model predictive control (NMPC) and proposes an actively improved Gaussian process (GP) model building strategy for incomplete models. The proposed method utilizes Bayesian optimization and expected improvement strategy to efficiently build models with insufficient initial training data for NMPC. It also considers multi-step ahead prediction and a novel disturbance rejection strategy based on GP outputs. Simulation results demonstrate the effectiveness of the proposed method compared to traditional algorithms.
Modelling is a basic and key requirement for model-based controlling, monitoring, or other process strategies. In non-linear model predictive control (NMPC), although data-driven models can be more easily established than first-principle ones, representative data may not be adequately included in advance to train a complete model, which is an attractive research topic. An actively improved Gaussian process (GP) model building strategy is developed, especially for incomplete models based on the idea of Bayesian optimization. The GP model can be used online as the internal model of model predictive control (MPC) directly. The model-building objective is based on the expected improvement strategy, which can exploit information gained from the currently gathered data as well as explore uncharted regions. The proposed method is a real-time design of experiments based on variance information of GP for efficient model building with insufficient initial training data for NMPC. Multi-step ahead prediction model is considered to give full play to predicting features of NPMC. Besides, a novel disturbance rejection strategy is also proposed based on GP outputs. Two simulation results, including comparisons with some traditional algorithms, are presented to demonstrate the effectiveness of the proposed method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据