Adaptive nonlinear optimal control for active suppression of airfoil flutter via a novel neural-network-based controller

Abstract

to-an-institutional-repository-green-openaccess Posting to an Institutional Repository (Green Open Access) Institutional Repositories: Information for SAGE Authors and Users Green Open Access: subscription journal articles deposited in institutional repositories Information for Authors Authors of articles published in subscription journals may share and reuse their article as outlined on the Guidelines for SAGE Authors page and stated in their signed Contributor Agreements. Under SAGE's Green Open Access policy, the Accepted Version of the article may be posted in the author's institutional repository and reuse is restricted to non-commercial and no derivative uses. For information about funding agency Open Access policies and ensuring compliance of agency-funded articles, see our Funding bodies, policies and compliance page. Information for Users of the Institutional Repository Users who receive access to an article through a repository are reminded that the article is protected by copyright and reuse is restricted to non-commercial and no derivative uses. Users may also download and save a local copy of an article accessed in an institutional repository for the user's personal reference. For permission to reuse an article, please follow our Process for Requesting Permission.

A neural network approach for improving airfoil active flutter suppression under control-input constraints

“…In particular, the required number of NNs can significantly increase with nonlinearities of higher orders and can result in heavy computational load under a complex controller structure, rendering online implementation impractical. Accordingly, an MVFA as in Tang et al (2018), which yields a simplified NN control structure suitable for online implementation, is introduced specifically for AFS as…”

“…Remark 2. Note that the work of Tang et al (2018) does not consider CICs. For the first time, in this study, the MVFA is used with a performance cost involving the generalized nonquadratic functional as in ( 5) to solve for optimal control under CICs.…”

“…Brillante and Mannarino (2016) used two recurrent NNs for system identification and control. Tang et al (2018) made further improvement to AFS by deriving an algorithm powered by two NNs to synthesize nonlinear optimal control in real time. A thorough review on AFS is provided by Livne (2018).…”

“…Therefore, in this study we focus on optimal AFS under CICs. Although the work of Tang et al (2018) offers an NOCOS solution to AFS, it does not take CICs into account, and this can result in failure to suppress flutter under CICs. Accordingly, this study makes use of some fundamentals from Tang et al (2018)…”

Dynamic response and vibration suppression of a cantilevered pipe conveying fluid under periodic excitation

“…Studies on the vibration control can be approximately classified into two types. One is the feedback control which usually requires accurate models, such as adjusting a proportional–integral–derivative controller by optimization algorithm (Saad et al., 2013), model predictive control (Lin and Huang, 2016), independent modal space control (Lin et al., 2004; Cinquemani and Resta, 2013), adaptive modal space control (Tsai and Lin, 1997), using a nonlinear energy sink for vibration control (Yang et al., 2013; Mamaghani et al., 2016), adaptive robust control using piezoelectric layer as sensor and actuator (Khajehpour et al., 2015), neural network control (Tang et al., 2018), and so on. The other is feedforward controls that do not have such high requirements on the model and do not need additional sensors.…”