Elektrik Elektronik Mühendisliği Bölümü Yayın Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/411
Browse
Search Results
Article Citation - WoS: 1Citation - Scopus: 2Dynamical System Parameter Identification Using Deep Recurrent Cell Networks Which Gated Recurrent Unit and When(Springer London Ltd, 2021) Akagunduz, Erdem; Cifdaloz, OguzhanIn this paper, we investigate the parameter identification problem in dynamical systems through a deep learning approach. Focusing mainly on second-order, linear time-invariant dynamical systems, the topic of damping factor identification is studied. By utilizing a six-layer deep neural network with different recurrent cells, namely GRUs, LSTMs or BiLSTMs; and by feeding input/output sequence pairs captured from a dynamical system simulator, we search for an effective deep recurrent architecture in order to resolve the damping factor identification problem. Our study's results show that, although previously not utilized for this task in the literature, bidirectional gated recurrent cells (BiLSTMs) provide better parameter identification results when compared to unidirectional gated recurrent memory cells such as GRUs and LSTM. Thus, indicating that an input/output sequence pair of finite length, collected from a dynamical system and when observed anachronistically, may carry information in both time directions to predict a dynamical systems parameter.Conference Object Management of Open-Access Renewable Resources With Depensation Dynamics: Control Systems Perspective(Ieee, 2021) Cifdaloz, OguzhanRenewable resources are being over exploited at an increasing rate. Institutions/governments are compelled to devise effective policies and strategies to sustainably manage renewable resources under social, ecological and environmental pressures that stem from increasing demand, model uncertainties, disturbances, and measurement errors. Open-access policies to harvest renewable resources are still widely used around the world. They are mildly regulated by implementing landing quotas, defining harvesting seasons, and/or constraining the technology used for harvesting. In many parts of the world, including the regions that are highly developed, open-access fisheries a refailing. In this paper, management of an open-access renewable resource (fishery) with depensation dynamics is formulated as a control systems problem and a strategy to sustainably manage the renewable resource is proposed. First, dynamics of an unregulated open-access fishery is described and its vulnerabilities are stated. Then, an easy-to-implement regulation strategy based on classical control systems ideas is proposed and its robustness characteristics are provided. The management policy (control law) is implemented via manipulating economic variables, i.e. by adjusting the (opportunity) cost of harvesting. An agent-based model is used to model the resource exploiters (i.e. fishermen). It is shown that a classical control law can be used to effectively manage an open access fishery subject to sampling effects.