A liquefied natural gas (LNG) facility often incorporates replicate liquefaction trains. The performance of equivalent units across trains, designed using common numerical models, might be expected to be similar. In this article, we discuss statistical analysis of real plant data to validate this assumption. Analysis of operational data for end flash vessels from a pair of replicate trains at an LNG facility indicates that one train produces 2.8%–6.4% more end flash gas than the other. We then develop statistical models for train operation, facilitating reduced flaring and hence a reduction of up to 45% in CO2 equivalent flaring emissions, noting that flaring emissions for a typical LNG facility account for ~4%–8% of the overall facility emissions. We recommend that operational data-driven models be considered generally to improve the performance of LNG facilities and reduce their CO2 footprint, particularly when replica units are present.

Surrogate models of turbulent diffusive flames could play a strategic role in the design of liquid rocket engine combustion chambers. The present article introduces a method to obtain data-driven surrogate models for coaxial injectors, by leveraging an inductive transfer learning strategy over a U-Net with available multifidelity Large Eddy Simulations (LES) data. The resulting models preserve reasonable accuracy while reducing the offline computational cost of data-generation. First, a database of about 100 low-fidelity LES simulations of shear-coaxial injectors, operating with gaseous oxygen and gaseous methane as propellants, has been created. The design of experiments explores three variables: the chamber radius, the recess-length of the oxidizer post, and the mixture ratio. Subsequently, U-Nets were trained upon this dataset to provide reasonable approximations of the temporal-averaged two-dimensional flow field. Despite the fact that neural networks are efficient non-linear data emulators, in purely data-driven approaches their quality is directly impacted by the precision of the data they are trained upon. Thus, a high-fidelity (HF) dataset has been created, made of about 10 simulations, to a much greater cost per sample. The amalgamation of low and HF data during the the transfer-learning process enables the improvement of the surrogate model’s fidelity without excessive additional cost.

This study introduces an advanced reinforcement learning (RL)-based control strategy for heating, ventilation, and air conditioning (HVAC) systems, employing a soft actor-critic agent with a customized reward mechanism. This strategy integrates time-varying outdoor temperature-dependent weighting factors to dynamically balance thermal comfort and energy efficiency. Our methodology has undergone rigorous evaluation across two distinct test cases within the building optimization testing (BOPTEST) framework, an open-source virtual simulator equipped with standardized key performance indicators (KPIs) for performance assessment. Each test case is strategically selected to represent distinct building typologies, climatic conditions, and HVAC system complexities, ensuring a thorough evaluation of our method across diverse settings. The first test case is a heating-focused scenario in a residential setting. Here, we directly compare our method against four advanced control strategies: an optimized rule-based controller inherently provided by BOPTEST, two sophisticated RL-based strategies leveraging BOPTEST’s KPIs as reward references, and a model predictive control (MPC)-based approach specifically tailored for the test case. Our results indicate that our approach outperforms the rule-based and other RL-based strategies and achieves outcomes comparable to the MPC-based controller. The second scenario, a cooling-dominated environment in an office setting, further validates the versatility of our strategy under varying conditions. The consistent performance of our strategy across both scenarios underscores its potential as a robust tool for smart building management, adaptable to both residential and office environments under different climatic challenges.

Numerical solutions of partial differential equations require expensive simulations, limiting their application in design optimization, model-based control, and large-scale inverse problems. Surrogate modeling techniques aim to decrease computational expense while retaining dominant solution features and characteristics. Existing frameworks based on convolutional neural networks and snapshot-matrix decomposition often rely on lossy pixelization and data-preprocessing, limiting their effectiveness in realistic engineering scenarios. Recently, coordinate-based multilayer perceptron networks have been found to be effective at representing 3D objects and scenes by regressing volumetric implicit fields. These concepts are leveraged and adapted in the context of physical-field surrogate modeling. Two methods toward generalization are proposed and compared: design-variable multilayer perceptron (DV-MLP) and design-variable hypernetworks (DVH). Each method utilizes a main network which consumes pointwise spatial information to provide a continuous representation of the solution field, allowing discretization independence and a decoupling of solution and model size. DV-MLP achieves generalization through the use of a design-variable embedding vector, while DVH conditions the main network weights on the design variables using a hypernetwork. The methods are applied to predict steady-state solutions around complex, parametrically defined geometries on non-parametrically-defined meshes, with model predictions obtained in less than a second. The incorporation of random Fourier features greatly enhanced prediction and generalization accuracy for both approaches. DVH models have more trainable weights than a similar DV-MLP model, but an efficient batch-by-case training method allows DVH to be trained in a similar amount of time as DV-MLP. A vehicle aerodynamics test problem is chosen to assess the method’s feasibility. Both methods exhibit promising potential as viable options for surrogate modeling, being able to process snapshots of data that correspond to different mesh topologies.

We introduce a comprehensive data-driven framework aimed at enhancing the modeling of physical systems, employing inference techniques and machine-learning enhancements. As a demonstrative application, we pursue the modeling of cathodic electrophoretic deposition, commonly known as e-coating. Our approach illustrates a systematic procedure for enhancing physical models by identifying their limitations through inference on experimental data and introducing adaptable model enhancements to address these shortcomings. We begin by tackling the issue of model parameter identifiability, which reveals aspects of the model that require improvement. To address generalizability, we introduce modifications, which also enhance identifiability. However, these modifications do not fully capture essential experimental behaviors. To overcome this limitation, we incorporate interpretable yet flexible augmentations into the baseline model. These augmentations are parameterized by simple fully-connected neural networks, and we leverage machine-learning tools, particularly neural ordinary differential equations, to learn these augmentations. Our simulations demonstrate that the machine-learning-augmented model more accurately captures observed behaviors and improves predictive accuracy. Nevertheless, we contend that while the model updates offer superior performance and capture the relevant physics, we can reduce off-line computational costs by eliminating certain dynamics without compromising accuracy or interpretability in downstream predictions of quantities of interest, particularly film thickness predictions. The entire process outlined here provides a structured approach to leverage data-driven methods by helping us comprehend the root causes of model inaccuracies and by offering a principled method for enhancing model performance.

Deep learning (DL) has become the most effective machine learning solution for addressing and accelerating complex problems in various fields, from computer vision and natural language processing to many more. Training well-generalized DL models requires large amounts of data which allows the model to learn the complexity of the task it is being trained to perform. Consequently, performance optimization of the deep-learning models is concentrated on complex architectures with a large number of tunable model parameters, in other words, model-centric techniques. To enable training such large models, significant effort has also gone into high-performance computing and big-data handling. However, adapting DL to tackle specialized domain-related data and problems in real-world settings presents unique challenges that model-centric techniques do not suffice to optimize. In this paper, we tackle the problem of developing DL models for seismic imaging using complex seismic data. We specifically address developing and deploying DL models for salt interpretation using seismic images. Most importantly, we discuss how looking beyond model-centric and leveraging data-centric strategies for optimization of DL model performance was crucial to significantly improve salt interpretation. This technique was also key in developing production quality, robust and generalized models.

Vibration-based structural health monitoring (SHM) of (large) infrastructure through operational modal analysis (OMA) is a commonly adopted strategy. This is typically a four-step process, comprising estimation, tracking, data normalization, and decision-making. These steps are essential to ensure structural modes are correctly identified, and results are normalized for environmental and operational variability (EOV). Other challenges, such as nonstructural modes in the OMA, for example, rotor harmonics in (offshore) wind turbines (OWTs), further complicate the process. Typically, these four steps are considered independently, making the method simple and robust, but rather limited in challenging applications, such as OWTs. Therefore, this study aims to combine tracking, data normalization, and decision-making through a single machine learning (ML) model. The presented SHM framework starts by identifying a “healthy” training dataset, representative of all relevant EOV, for all structural modes. Subsequently, operational and weather data are used for feature selection and a comparative analysis of ML models, leading to the selection of tree-based learners for natural frequency prediction. Uncertainty quantification (UQ) is introduced to identify out-of-distribution instances, crucial to guarantee low modeling error and ensure only high-fidelity structural modes are tracked. This study uses virtual ensembles for UQ through the variance between multiple truncated submodel predictions. Practical application to monopile-supported OWT data demonstrates the tracking abilities, separating structural modes from rotor dynamics. Control charts show improved decision-making compared to traditional reference-based methods. A synthetic dataset further confirms the approach’s robustness in identifying relevant natural frequency shifts. This study presents a comprehensive data-driven approach for vibration-based SHM.