The modeling of multiphase flow in a pipe presents a significant challenge for high-resolution computational fluid dynamics (CFD) models due to the high aspect ratio (length over diameter) of the domain. In subsea applications, the pipe length can be several hundreds of meters vs a pipe diameter of just a few inches. Approximating CFD models in a low-dimensional space, reduced-order models have been shown to produce accurate results with a speed-up of orders of magnitude. In this paper, we present a new AI-based non-intrusive reduced-order model within a domain decomposition framework (AI-DDNIROM), which is capable of making predictions for domains significantly larger than the domain used in training. This is achieved by (i) using a domain decomposition approach; (ii) using dimensionality reduction to obtain a low-dimensional space in which to approximate the CFD model; (iii) training a neural network to make predictions for a single subdomain; and (iv) using an iteration-by-subdomain technique to converge the solution over the whole domain. To find the low-dimensional space, we compare Proper Orthogonal Decomposition with several types of autoencoder networks, known for their ability to compress information accurately and compactly. The comparison is assessed with two advection-dominated problems: flow past a cylinder and slug flow in a pipe. To make predictions in time, we exploit an adversarial network, which aims to learn the distribution of the training data, in addition to learning the mapping between particular inputs and outputs. This type of network has shown the potential to produce visually realistic outputs. The whole framework is applied to multiphase slug flow in a horizontal pipe for which an AI-DDNIROM is trained on high-fidelity CFD simulations of a pipe of length 10 m with an aspect ratio of 13:1 and tested by simulating the flow for a pipe of length 98 m with an aspect ratio of almost 130:1. Inspection of the predicted liquid volume fractions shows a good match with the high fidelity model as shown in the results. Statistics of the flows obtained from the CFD simulations are compared to those of the AI-DDNIROM predictions to demonstrate the accuracy of our approach.

Parameter optimization, also referred to as design closure, is imperative in the development of modern antennas. Theoretical considerations along with rough dimension adjustment through supervised parameter sweeping can only yield initial designs that need to be further tuned to boost the antenna performance. The major challenges include handling of multi-dimensional parameter spaces while accounting for several objectives and constraints. Due to complexity of modern antenna topologies, parameter interactions are often involved, leading to multiple local optima as well as difficulties in identifying decent initial designs that can be improved using local procedures. In such cases, global search is required, which is an expensive endeavor, especially if full-wave electromagnetic (EM) analysis is employed for antenna evaluation. This paper proposes a novel technique accommodating the search space exploration using local kriging surrogates and local improvement by means of trust-region gradient search. Computational efficiency of the process is achieved by constructing the metamodels over appropriately defined affine subspaces and incorporation of coarse-mesh EM simulations at the exploratory stages of the optimization process. The resulting framework enables nearly global search capabilities at the costs comparable to conventional gradient-based local optimization. This is demonstrated using two antenna examples and comparative studies involving multiple-start local tuning.

Parametric optimization is a mandatory step in the design of contemporary antenna structures. Conceptual development can only provide rough initial designs that have to be further tuned, often extensively. Given the topological complexity of modern antennas, the design closure necessarily involves full-wave electromagnetic (EM) simulations and—in many cases—global search procedures. Both factors make antenna optimization a computationally expensive endeavor: population-based metaheuristics, routinely used in this context, entail significant computational overhead. This letter proposes a novel approach that interleaves trust-region gradient search with iterative parameter space exploration by means of local kriging surrogate models. Dictated by efficiency, the latter are rendered in low-dimensional subspaces spanned by the principal components of the antenna response Jacobian matrix, extracted to identify the directions of the maximum (frequency-averaged) response variability. The aforementioned combination of techniques enables quasi-global search at the cost comparable to local optimization. These features are demonstrated using two antenna examples as well as benchmarking against multiple-start local tuning.

Optimization-based parameter tuning has become an inherent part of contemporary antenna design process. For the sake of reliability, it is typically conducted at the level of full-wave electromagnetic (EM) simulation models. This may incur considerable computational expenses depending on the cost of an individual EM analysis, the number of adjustable variables, the type of task (local, global, single-/multi-objective optimization), and the constraints involved. For these reasons, utilization of conventional algorithms is often impractical. This paper proposes a novel gradient-based algorithm with numerical derivatives for expedited antenna optimization. The improvement of computational efficiency is obtained by employing a rank-one Broyden formula and restricting finite differentiation sensitivity updates to the principal directions of the Jacobian matrix, i.e., those corresponding to the most significant changes of the antenna responses. Comprehensive numerical validation carried out using three wideband antennas indicates that the presented methodology offers considerable savings of sixty percent with respect to the reference trust-region algorithm. At the same time, virtually no degradation of the design quality is observed. Furthermore, algorithm reliability is greatly improved (while offering comparable computational efficiency) over the recent state-of-the-art accelerated gradient-based procedures.