Mandar Tabib

A computationally efficient predictive digital twin (DT) of a small-scale greenhouse needs an accurate and faster modelling of key variables such as the temperature field and flow field within the greenhouse. This involves: (a) optimally placing sensors in the experimental set-up and (b) developing fast predictive models. In this work, for a greenhouse set-up, the former requirement fulfilled first by identifying the optimal sensor locations for temperature measurements using the QR column pivoting on a tailored basis. Here, the tailored basis is the low-dimensional representation of hi-fidelity computational fluid dynamics (CFD) flow data, and these tailored basis are obtained using proper orthogonal decomposition (POD). To validate the method, the full temperature field inside the greenhouse is then reconstructed for an unseen parameter (inflow condition) using the temperature values from a few synthetic sensor locations in the CFD model. To reconstruct the flow-fields using a faster predictive model than the hi-fidelity CFD model, a long-short term memory (LSTM) method based on a reduced-order model (ROM) is used. The LSTM learns the temporal dynamics of coefficients associated with the POD-generated velocity basis modes. The LSTM-POD ROM model is used to predict the temporal evolution of velocity fields for our DT case, and the predictions are qualitatively similar to those obtained from hi-fidelity numerical models. Thus, the two data-driven tools have shown potential in enabling the forecasting and monitoring of key variables in a digital twin of a greenhouse. In future work, there is scope for improvements in the reconstruction accuracy by involving deep-learning-based corrective source term approaches.

In this study, we present a parametric, non-intrusive reduced order modeling (NIROM) framework as a potential digital-twin enabler for fluid flow around an aerofoil. A wind turbine blade has its basic foundation in the aerofoil shape. A faster way of understanding dynamic flow changes around the aerofoil-shaped blade can help make quick decisions related to wind-turbine operations and lead to optimal aerodynamic performance and power production. In this direction, a case study involving the application of the NIROM methodology for flow prediction around a NACA 0015 aerofoil is considered. The Reynolds number (Re) is the varying parameter, ranging from 320 000 to 1.12 million and high-fidelity CFD simulations are performed to generate the database for developing the NIROM. The aforementioned NIROM framework employs a Grassmann manifold interpolation approach (GI) for obtaining basis functions corresponding to new values of the parameter (Reynolds number), and exploits the time series prediction capabilities of the long short-term memory (LSTM) recurrent neural network for obtaining temporal coefficients associated with the new basis functions. The methodology involves: (a) an offline training phase, where the LSTM model is trained on the modal coefficients extracted from the sampled high-resolution data using the proper orthogonal decomposition (POD), and (b) an online testing phase, where for the new parameter value, the corresponding flow field is obtained using the GI-modulated basis functions for new parameter and the LSTM-predicted temporal coefficients. The NIROM-approximated flow predictions at new parameters have been compared to the high-dimensional full-order model (FOM) solutions for the high-Re aerofoil case and for a low-Re number wake vortex merger case in order to put the performance of NIROM in perspective. The results indicate that the NIROM framework can qualitatively predict the complex flow scenario around the aerofoil for new values of Reynolds number, while it has quantitatively shown that the LSTM predictions improve with the enrichment of the training space. For the low-Re vortex merger case, NIROM works very well. Thus, it can be deduced that there is scope and potential for continued research in NIROMs as digital twin enablers in wind energy applications.

Digital twins are meant to bridge the gap between real-world physical systems and virtual representations. Both stand-alone and descriptive digital twins incorporate 3D geometric models, which are the physical representations of objects in the digital replica. Digital twin applications are required to rapidly update internal parameters with the evolution of their physical counterpart. Due to an essential need for having high-quality geometric models for accurate physical representations, the storage and bandwidth requirements for storing 3D model information can quickly exceed the available storage and bandwidth capacity. In this work, we demonstrate a novel approach to geometric change detection in a digital twin context. We address the issue through a combined solution of dynamic mode decomposition (DMD) for motion detection, YOLOv5 for object detection, and 3D machine learning for pose estimation. DMD is applied for background subtraction, enabling detection of moving foreground objects in real-time. The video frames containing detected motion are extracted and used as input to the change detection network. The object detection algorithm YOLOv5 is applied to extract the bounding boxes of detected objects in the video frames. Furthermore, we estimate the rotational pose of each object in a 3D pose estimation network. A series of convolutional neural networks (CNNs) conducts feature extraction from images and 3D model shapes. Then, the network outputs the camera orientation’s estimated Euler angles concerning the object in the input image. By only storing data associated with a detected change in pose, we minimize necessary storage and bandwidth requirements while still recreating the 3D scene on demand. Our assessment of the new geometric detection framework shows that the proposed methodology could represent a viable tool in emerging digital twin applications.

We put forth a long short-term memory (LSTM) nudging framework for the enhancement of reduced order models (ROMs) of fluid flows utilizing noisy measurements for air traffic improvements. Toward emerging applications of digital twins in aviation, the proposed approach allows for constructing a realtime predictive tool for wake-vortex transport and decay systems. We build on the fact that in realistic application, there are uncertainties in initial and boundary conditions, model parameters, as well as measurements. Moreover, conventional nonlinear ROMs based on Galerkin projection (GROMs) suffer from imperfection and solution instabilities, especially for advection-dominated flows with slow decay in the Kolmogorov width. In the presented LSTM nudging (LSTM-N) approach, we fuse forecasts from a combination of imperfect GROM and uncertain state estimates, with sparse Eulerian sensor measurements to provide more reliable predictions in a dynamical data assimilation framework. We illustrate our concept by solving a two-dimensional vorticity transport equation. We investigate the effects of measurements noise and state estimate uncertainty on the performance of the LSTM-N behavior. We also demonstrate that it can sufficiently handle different levels of temporal and spatial measurement sparsity, and offer a huge potential in developing next-generation digital twin technologies.