Stochastic gradient based extreme learning machines for stable online learning of advanced combustion engines

NEUROCOMPUTING

卷:177

Article

Janakiraman, Vijay Manikandan¹  Nguyen, XuanLong²  Assanis, Dennis^3,4,5 

[1] Univ Michigan, Dept Mech Engn, Ann Arbor, MI 48109 USA

[2] Univ Michigan, Dept Stat, Ann Arbor, MI 48109 USA

[3] SUNY Stony Brook, Dept Mech Engn, Stony Brook, NY USA

[4] SUNY Stony Brook, Acad Affairs, Stony Brook, NY USA

[5] SUNY Stony Brook, Brookhaven Affairs, Stony Brook, NY USA

关键词: Online learning;    Extreme learning machine;    System identification;    Lyapunov stability;    Engine control;    Operating envelope;   

DOI  :  10.1016/j.neucom.2015.11.024

来源: Elsevier

【 摘 要 】

We propose and develop SG-ELM, a stable online learning algorithm based on stochastic gradients and Extreme Learning Machines (ELM). We propose SG-ELM particularly for systems that are required to be stable during learning; i.e., the estimated model parameters remain bounded during learning. We use a Lyapunov approach to prove both asymptotic stability of estimation error and boundedness in the model parameters suitable for identification of nonlinear dynamic systems. Using the Lyapunov approach, we determine an upper bound for the learning rate of SG-ELM. The SG-ELM algorithm not only guarantees a stable learning but also reduces the computational demand compared to the recursive least squares based OS-ELM algorithm (Liang et al., 2006). In order to demonstrate the working of SG-ELM on a real world problem, an advanced combustion engine identification is considered. The algorithm is applied to two case studies: An online regression learning for system identification of a Homogeneous Charge Compression Ignition (HCCI) Engine and an online classification learning (with class imbalance) for identifying the dynamic operating envelope. The case studies demonstrate that the accuracy of the proposed SG-ELM is comparable to that of the OS-ELM approach but adds stability and a reduction in computational effort. (C) 2015 Elsevier B.V. All rights reserved.

【 授权许可】

Free