期刊
出版社
ROYAL SOC
DOI: 10.1098/rspa.2018.0335
关键词
model predictive control; nonlinear dynamics; sparse identification of nonlinear dynamics; system identification; control theory; machine learning
资金
- Washington Research Foundation
- Gordon and Betty Moore Foundation [2013-10-29]
- Alfred P. Sloan Foundation [3835]
- University of Washington eScience Institute
- Defense Advanced Research Projects Agency (DARPA) [HR011-16-C-0016, PA-18-01-FP-125]
- Army Research Office [W911NF-17-1-0306, W911NF-17-1-0422]
- Air Force Office of Scientific Research [FA9550-17-1-0329]
Data-driven discovery of dynamics via machine learning is pushing the frontiers of modelling and control efforts, providing a tremendous opportunity to extend the reach ofmodel predictive control (MPC). However, many leadingmethods in machine learning, such as neural networks (NN), require large volumes of training data, may not be interpretable, do not easily include known constraints and symmetries, and may not generalize beyond the attractor where models are trained. These factors limit their use for the online identification of a model in the low-data limit, for example following an abrupt change to the system dynamics. In this work, we extend the recent sparse identification of nonlinear dynamics (SINDY) modelling procedure to include the effects of actuation and demonstrate the ability of these models to enhance the performance of MPC, based on limited, noisy data. SINDY models are parsimonious, identifying the fewest terms in the model needed to explain the data, making them interpretable and generalizable. We show that the resulting SINDY-MPC framework has higher performance, requires significantly less data, and is more computationally efficient and robust to noise than NN models, making it viable for online training and execution in response to rapid system changes. SINDY-MPC also shows improved performance over linear data-driven models, although linear models may provide a stopgap until enough data is available for SINDY. SINDY-MPC is demonstrated on a variety of dynamical systems with different challenges,including the chaotic Lorenz system, a simple model for flight control of an F8 aircraft, and an HIV model incorporating drug treatment.
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