Mechanical Engineering
Permanent URI for this communityhttp://hdl.handle.net/1903/2263
Browse
12 results
Search Results
Item Analyzing Inverse Design Problems from a Topological Perspective(2024) Chen, Qiuyi; Fuge, Mark; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Inverse design (ID) problems are inverse problems that aim to rapidly retrieve the subset of valid designs having the desired performances and properties under the given conditions. In practice, this can be solved by training generative models to approximate and sample the posterior distributions of designs. However, little has been done to understand their mechanisms and limitations from a theoretical perspective. This dissertation leverages theoretical tools from general and differential topology to answer these three questions of inverse design: what does a set of valid designs look like? How helpful are the data-driven generative models for retrieving the desired designs from this set? What topological properties affect the subset of desired designs? The dissertation proceeds by dismantling inverse (design) problems into two major subjects: that is, the representing and probing of a given set of valid designs (or data), and the retrieval of the desired designs (or data) from this given set. It draws inspiration from topology and geometry to investigate them and makes the main contributions below: 1. Chapter 3 details a novel representation learning method called Least Volume, which has properties similar to nonlinear PCA for representing datasets. It can minimize the representation's dimension automatically and, as shown in Chapter 4, conducts contrastive learning when applied to labeled datasets. 2. Two conditional generative models are developed to generate performant 2-D airfoils and 3-D heat sinks in Chapter 5 and 6 respectively. They can produce realistic designs to warm-start further optimization, with the relevant chapters detailing their acceleration effects. 3. Lastly, Chapter 7 describes how to use Least volume to solve high-dimensional inverse problems efficiently. Specifically, using examples from physic system identification, the chapter uncovers the correlation between the inverse problem's uncertainty and its intrinsic dimensions.Item OPTIMAL PROBING OF BATTERY CYCLES FOR MACHINE LEARNING-BASED MODEL DEVELOPMENT(2024) Nozarijouybari, Zahra; Fathy, Hosam HF; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)This dissertation examines the problems of optimizing the selection of the datasets and experiments used for parameterizing machine learning-based electrochemical battery models. The key idea is that data selection, or “probing” can empower such models to achieve greater fidelity levels. The dissertation is motivated by the potential of battery models to enable theprediction and optimization of battery performance and control strategies. The literature presents multiple battery modeling approaches, including equivalent circuit, physics-based, and machine learning models. Machine learning is particularly attractive in the battery systems domain, thanks to its flexibility and ability to model battery performance and aging dynamics. Moreover, there is a growing interest in the literature in hybrid models that combine the benefits of machine learning with either the simplicity of equivalent circuit models or the predictiveness of physics-based models or both. The focus of this dissertation is on both hybrid and purely data-driven battery models. Moreover, the overarching question guiding the dissertation is: how does the selection of the datasets and experiments used for parameterizing these models affect their fidelity and parameter identifiability? Parameter identifiability is a fundamental concept from information theory that refers to the degree to which one can accurately estimate a given model’s parameters from input-output data. There is substantial existing research in the literature on battery parameter identifiability. An important lesson from this literature is that the design of a battery experiment can affect parameter identifiability significantly. Hence, test trajectory optimization has the potential to substantially improve model parameter identifiability. The literature explores this lesson for equivalent circuit and physics-based battery models. However, there is a noticeable gap in the literature regarding identifiability analysis and optimization for both machine learning-based and hybrid battery models. To address the above gap, the dissertation makes four novel contributions to the literature. The first contribution is an extensive survey of the machine learning-based battery modeling literature, highlighting the critical need for information-rich and clean datasets for parameterizing data-driven battery models. The second contribution is a K-means clustering-based algorithm for detecting outlier patterns in experimental battery cycling data. This algorithm is used for pre-cleaning the experimental cycling datasets for laboratory-fabricated lithium-sulfur (Li-S) batteries, thereby enabling the higher-fidelity fitting of a neural network model to these datasets. The third contribution is a novel algorithm for optimizing the cycling of a lithium iron phosphate (LFP) to maximize the parameter identifiability of a hybrid model of this battery. This algorithm succeeds in improving the resulting model’s Fisher identifiability significantly in simulation. The final contribution focuses on the application of such test trajectory optimization to the experimental cycling of commercial LFP cells. This work shows that test trajectory optimization is s effective not just at improving parameter identifiability, but also at probing and uncovering higher-order battery dynamics not incorporated in the initial baseline model. Collectively, all four of these contributions show the degree to which the selection of battery cycling datasets and experiments for richness and cleanness can enable higher-fidelity data-driven and hybrid modeling, for multiple battery chemistries.Item Denoising the Design Space: Diffusion Models for Accelerated Airfoil Shape Optimization(2024) Diniz, Cashen; Fuge, Mark D; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Generative models offer the possibility to accelerate and potentially substitute parts of the often expensive traditional design optimization process. We present Aero-DDM, a novel application of a latent denoising diffusion model (DDM) capable of generating airfoil geometries conditioned on flow parameters and an area constraint. Additionally, we create a novel, diverse dataset of optimized airfoil designs that better reflects a realistic design space than has been done in previous work. Aero-DDM is applied to this dataset, and key metrics are assessed both statistically and with an open-source computational fluid dynamics (CFD) solver to determine the performance of the generated designs. We compare our approach to an optimal transport GAN, and demonstrate that our model can generate designs with superior performance statistically, in aerodynamic benchmarks, and in warm-start scenarios. We also extend our diffusion model approach, and demonstrate that the number of steps required for inference can be reduced by as much as ~86%, compared to an optimized version of the baseline inference process, without meaningful degradation in design quality, simply by using the initial design to start the denoising process.Item TOWARDS AUTOMATION OF HEMORRHAGE DIAGNOSTICS AND THERAPEUTICS(2024) Chalumuri, Yekanth Ram; Hahn, Jin-Oh; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The main aim of the thesis is to advance the technology in the development ofalgorithms and methodologies that will advance the care in hemorrhage diagnostics and therapeutics in low resource settings. The first objective of this thesis is to develop algorithms to primarily detect internal hemorrhage using non-invasive multi-modal physiological sensing. We developed a machine learning algorithm that can classify various types of hypovolemia and is shown to be performing superior to the algorithms developed primarily based on vital signs. To address the limitations in the data-driven approaches, we explored physics-based approaches to detect internal hemorrhage. In silico analysis showed that our physics-based algorithms can not only detect hemorrhage but also can detect hemorrhage even when hemorrhage is being compensated by fluid resuscitation. The second objective is to advance the regulatory aspects of physiological closed-loopcontrol systems in maintaining blood pressure at a desired value during hemorrhage and resuscitation. Physiological closed-loop control systems offer an exciting opportunity to treat hemorrhage in low resource settings but often face regulatory challenges due to safety concerns. A physics-based model with rigorous validation can improve regulatory aspects of such systems but current validation techniques are very naive. We developed a physics-based model that can predict hemodynamics during hemorrhage and resuscitation and validated these factors using a validation framework that uses sampled digital twins. Then we utilized the validated model to evaluate its efficacy in predicting the performance capability of the model and virtual patient generator in predicting the closed-loop controller metrics of unseen experimental data. To summarize, we tried to improve the hemorrhage care using novel algorithmdevelopment and in silico validation and evaluation of computation models that can be used to treat hemorrhage.Item Ordering Non-Linear Subspaces for Airfoil Design and Optimization via Rotation Augmented Gradients(2023) Van Slooten, Alec; Fuge, Mark; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Airfoil optimization is critical to the design of turbine blades and aerial vehicle wings, among other aerodynamic applications. This design process is often constrained by the computational time required to perform CFD simulations on different design options, or the availability of adjoint solvers. A common method to mitigate some of this computational expense in nongradient optimization is to perform dimensionality reduction on the data and optimize the design within this smaller subspace. Although learning these low-dimensional airfoil manifolds often facilitates aerodynamic optimization, these subspaces are often still computationally expensive to explore. Moreover, the complex data organization of many current nonlinear models make it difficult to reduce dimensionality without model retraining. Inducing orderings of latent components restructures the data, reduces dimensionality reduction information loss, and shows promise in providing near-optimal representations in various dimensions while only requiring the model to be trained once. Exploring the response of airfoil manifolds to data and model selection and inducing latent component orderings have potential to expedite airfoil design and optimization processes. This thesis first investigates airfoil manifolds by testing the performance of linear and nonlinear dimensionality reduction models, examining if optimized geometries occupy lower dimensional manifolds than non-optimized geometries, and by testing if the learned representation can be improved by using target optimization conditions as data set features. We find that autoencoders, although often suffering from stability issues, have increased performance over linear methods such as PCA in low dimensional representations of airfoil databases. We also find that the use of optimized geometry and the addition of performance parameters have little effect on the intrinsic dimensionality of the data. This thesis then explores a recently proposed approach for inducing latent space orderings called Rotation Augmented Gradient (RAG) [1]. We extend their algorithm to nonlinear models to evaluate its efficacy at creating easily-navigable latent spaces with reduced training, increased stability, and improved design space preconditioning. Our extension of the RAG algorithm to nonlinear models has potential to expedite dimensional analyses in cases with near-zero gradients and long training times by eliminating the need to retrain the model for different dimensional subspacesItem Investigation of Swirl Distributed Combustion with Experimental Diagnostics and Artificial Intelligence Approach(2022) Roy, Rishi; Gupta, Ashwani K; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Swirl Distributed Combustion was fundamentally investigated with experimental diagnostics and predictive analysis using machine learning and computer vision techniques. Ultra-low pollutants emission, stable operation, improved pattern factor, and fuel flexibility make distributed combustion an attractive technology for potential applications in high-intensity stationary gas turbines. Proper mixing of inlet fresh air and hot products for creating a hot and low-oxygen environment is critical to foster distributed combustion, followed by rapid mixing with the fuel. Such conditions result in a distributed thick reaction zone without hotspots found in (thin reaction front) of conventional diffusion flames leading to reduced NOx and CO emissions. The focus of this dissertation is to develop a detailed fundamental understanding of distributed combustion in a lab-based swirl combustor (to mimic gas turbine can combustor) at moderate heat release intensities in the range 5.72- 9.53 MW/m3-atm using various low-carbon gaseous fuels such as methane, propane, hydrogen-enriched fuels. The study of distributed combustion at moderate thermal intensity helped to understand the fundamental aspects such as reduction of flame fluctuation, mitigation of thermo-acoustic instability, flame shape evolution, flow field behavior, turbulence characteristics, variation of Damkӧhler number, vortex propagation, flame blowoff, and pollutant and CO2 emission reduction with gradual mixture preparation. Initial efforts were made to obtain the volumetric distribution ratio, evolution of flame shape in terms of OH* radical imaging, variation of flame standoff, thermal field uniformity, and NO and CO emissions when the flame transitions to distributed reaction zone. Further investigation was performed to study the mitigation of flame thermo-acoustics and precession vortex core (PVC) instabilities in swirl distributed combustion compared to swirl air combustion using the acoustic pressure and qualitative heat release fluctuation data at different dilution CO2 dilution levels with and without air preheats. Proper orthogonal decomposition (POD) technique was utilized to visualize the appearance of dynamic coherent structures in reactive flow fields and reduction of fluctuation energy. Vortex shedding was found responsible for the fluctuation in swirl air combustion while no significant flame fluctuation was observed in distributed combustion. Distributed combustion showed significantly reduced acoustic noise and much higher stability quantified by local and global Rayleigh index. This study was extended with hydrogen-enriched methane (vol. = 0, 10, 20, 40% H2) to compare the stability of the flow field in conventional air combustion and distributed combustion. Results were consistent and distributed reaction zones showed higher flame stability compared to conventional swirl air combustion. The study of lean blowoff in distributed combustion showed a higher lean blowoff equivalence ratio with gradual increase in heat release intensity, which was attributed to higher flow field instability due to enhanced inlet turbulence. Extension of lean blowoff (ϕLBO) was observed with gradual %H2 which showed decrease of lean blowoff equivalence ratio in distributed reaction zones. Additionally, the reduction in ϕLBO was achieved by adding preheats to the inlet airstream for different H2 enrichment cases due to enhanced flame stability gained from preheating. Examination of non-reactive flow field with particle image velocimetry (PIV) was performed to understand the fundamental differences between swirl flow and distributed reaction flow at constant heat release intensities. Higher rms fluctuation leading to healthy turbulence and higher Reynolds stress were found in distributed reaction flow cases signifying enhanced mixing characteristics in distributed combustion. Reduction of pollutant emission was an important focus of this research. Measurement of NO and CO emission at different mixture preparation levels exhibited significant reduction in NO emission (single digit) compared to swirl air combustion due to mitigation of spatial hotspots and temperature peaks. Additionally, better mixing and uniform stoichiometry supported reduced CO emissions in distributed combustion for every fuel. With increased H2 in the fuel, NO gradually increased for air combustion while reduction of NO was found in distributed combustion due to decrease in thermal and prompt NO generation. Finally, the use of machine learning and computer vision techniques was investigated for software-based prediction of combustion parameters (pollutants and flame temperature) and feature-based recognition of distributed combustion regimes. The primary goal of using artificial intelligence is to reduce the time of experimentation and frequent manual interference during experiments in order to enhance the overall accuracy by reducing human errors. Such predictions will help in developing data-driven smart-sensing of combustion parameters and reduce the dependence on experimental trials.Item THERMODYNAMIC AND TRANSPORT PROPERTIES OF AVIATION TURBINE FUEL: PREDICTIVE APPROACHES USING ENTROPY SCALING GUIDED MACHINE LEARNING WITH EXPERIMENTAL VALIDATION(2022) Malatesta, William Anthony; Yang, Bao; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)With issues such as increasing power generation densities, design restrictions on heat rejection, and finite heat sink capacity, fighter aircraft face significant thermal management challenges which are driving research from component to system level technology regimes. As aviation turbine fuel often represents half of the take-off weight of aircraft, it is an integral piece of the thermal management puzzle and generally regarded as the primary internal heat sink for fighter aircraft. Though typical thermal performance analysis requires temperature dependent transport and thermodynamic properties of fuel, the variation in properties associated with the fact that fuels are mixtures with varying composition is not well understood. As such, the present work aimed to define bounds of density, viscosity, thermal conductivity, and specific heat of aviation turbine fuel as functions of composition and temperature by developing numerical models which were validated against test data. Data collected for this work included 96 samples with measured composition and viscosity at a single temperature (54 F-24, 26 JP-8, 11 Jet A, 5 Jet A-1), and four samples (3 JP-5 and 1 F-24) which underwent compositional and temperature dependent property testing. The novel modeling approaches to predict viscosity and thermal conductivity of jet fuels employed pseudo component entropy scaling techniques with artificial neural networks occupying an intermediate step in the overall model. Simple hyper-parameter optimization techniques were developed to promote model stability, computational efficiency, and long-term repeatability of the approach. Additionally, a model for predicting temperature dependent isobaric specific heats of liquids based on atomic density was developed for well-defined hydrocarbon mixtures. Model performance against test data showed average deviations of 0.1%, 1%, and -2% for viscosity, thermal conductivity, and specific heat respectively. Utilizing the compositional data collected, the models were then used to estimate bounds of these properties. Analysis of Prandtl numbers calculated using the modeled property ranges suggests that the observed variation in properties should be considered during a thorough aircraft thermal management design or performance analysis effort.Item Survey and Comparative Evaluation of Machine Learning Models for Performance Approximation of Tube-Fin Heat Exchangers(2021) Subbappa, Rajath; Aute, Vikrant C; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Tube-fin heat exchangers (TFHXs) are omnipresent within the air-conditioning and refrigeration industry. Computationally expensive, physics-based models are conventionally used to conduct performance simulations, optimization, and design selection of such devices. In this thesis, a comparative evaluation of machine learning based regression techniques to predict the heat transfer and refrigerant pressure drop of TFHXs for different applications is conducted. Ridge Regression, Support Vector Regression (SVR) and Artificial Neural Network (ANN) models are trained and analysed. Results show that the baseline full-domain SVR and ANN models predict more than 90% of the test dataset within a 20% error band for 5 out of 6 application cases. Subsequently, an outcome-based comparison framework is proposed to understand the cost incurred by an ML model in achieving a predetermined degree of accuracy. As a result, reduced-domain ANN and SVR models with training times that are 2 to 3 orders of magnitude lower than baseline models with little to no degradation in prediction accuracy are obtained. The trained ML models facilitate rapid exploration of the design space with significant reduction in engineering time to arrive at near optimal designs.Item NEXT GENERATION HEAT PUMP SYSTEM EVALUATION METHODOLOGIES(2021) Wan, Hanlong; Radermacher, Reinhard K.; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Energy consumption of heat pump (HP) systems plays a significant role in the global residential building energy sector. The conventional HP system evaluation method focused on the energy efficiency during a given time scale (e.g., hourly, seasonally, or annually). Nevertheless, these evaluation methods or test metrics are unable to fully reflect the thermodynamic characteristics of the system (e.g., the start-up process). In addition, previous researchers typically conducted HP field tests no longer than one year period. Only limited studies conducted the system performance tests over multiple years. Furthermore, the climate is changing faster than previously predicted beyond the irreversible and catastrophic tipping point. HP systems are the main contributor to global warming due to the increased demands but also can be a part of the solution by replacing fossil fuel burning heating systems. A holistic evaluation of the HP system’s global warming impact during its life cycle needs to account for the direct greenhouse gas (GHG) emissions from the refrigerant leakage, indirect GHG emissions from the power consumption and embodied equipment emissions. This dissertation leverages machine learning, deep learning, data digging, and Life Cycle Climate Performance (LCCP) approaches to develop next generation HP system evaluation methodologies with three thrusts: 1) field test data analysis, 2) data-driven modeling, and 3) enhanced life cycle climate performance (En-LCCP) analysis. This study made following observations: First, time-average performance metrics can save time in extensive data calculation, while quasi-steady-state performance metrics can elucidate some details of the studied system. Second, deep-learning-based algorithms have higher accuracy than conventional modeling approaches and can be used to analyze the system's dynamic performance. However, the complicated structure of the networks, numerous parameters needing optimization, and longer training time are the main challenges for these methods. Third, this dissertation improved current environmental impact evaluation method considering ambient conditions variation, local grid source structure, and next-generation low-GWP refrigerants, which led the LCCP results closer to reality and provided alternative methods for determining LCCP input parameters with limited-data cases. Future work could be studying the uncertainty within the deep learning networks and finding a general process for modeling settings. People may also develop a multi-objective optimization model for HP system design while considering both the LCCP and cost.Item Towards Trust and Transparency in Deep Learning Systems through Behavior Introspection & Online Competency Prediction(2021) Allen, Julia Filiberti; Gabriel, Steven A.; Mechanical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Deep neural networks are naturally “black boxes”, offering little insight into how or why they make decisions. These limitations diminish the adoption likelihood of such systems for important tasks and as trusted teammates. We employ introspective techniques to abstract machine activation patterns into human-interpretable strategies and identify relationships between environmental conditions (why), strategies (how), and performance (result) on both a deep reinforcement learning two-dimensional pursuit game application and image-based deep supervised learning obstacle recognition application. Pursuit-evasion games have been studied for decades under perfect information and analytically-derived policies for static environments. We incorporate uncertainty in a target’s position via simulated measurements and demonstrate a novel continuous deep reinforcement learning approach against speed-advantaged targets. The resulting approach was tested under many scenarios and performance exceeded that of a baseline course-aligned strategy. We manually observed separation of learned pursuit behaviors into strategy groups and manually hypothesized environmental conditions that affected performance. These manual observations motivated automation and abstraction of conditions, performance and strategy relationships. Next, we found that deep network activation patterns could be abstracted into human-interpretable strategies for two separate deep learning approaches. We characterized machine commitment by the introduction of a novel measure and revealed significant correlations between machine commitment, strategies, environmental conditions, and task performance. As such, we motivated online exploitation of machine behavior estimation for competency-aware intelligent systems. And finally, we realized online prediction capabilities for conditions, strategies, and performance. Our competency-aware machine learning approach is easily portable to new applications due to its Bayesian nonparametric foundation, wherein all inputs are compactly transformed into the same compact data representation. In particular, image data is transformed into a probability distribution over features extracted from the data. The resulting transformation forms a common representation for comparing two images, possibly from different types of sensors. By uncovering relationships between environmental conditions (why), machine strategies (how), & performance (result) and by giving rise to online estimation of machine competency, we increase transparency and trust in machine learning systems, contributing to the overarching explainable artificial intelligence initiative.