Physical Sciences and Mathematics Commons^™

Use Of Digital Twins To Mitigate Communication Failures In Microgrids, Andrew Eggebeen

Theses and Dissertations

This work investigates digital twin (DT) applications for electric power system (EPS) resilience. A novel DT architecture is proposed consisting of a physical twin, a virtual twin, an intelligent agent, and data communications. Requirements for the virtual twin are identified. Guidelines are provided for generating, capturing, and storing data to train the intelligent agent. The relationship between the DT development process and an existing controller hardware-in-the-loop (CHIL) process is discussed. To demonstrate the proposed DT architecture and development process, a DT for a battery energy storage system (BESS) is created based on the simulation of an industrial nanogrid. The creation …

A Design Strategy To Improve Machine Learning Resiliency Of Physically Unclonable Functions Using Modulus Process, Yuqiu Jiang

Theses and Dissertations

Physically unclonable functions (PUFs) are hardware security primitives that utilize non-reproducible manufacturing variations to provide device-specific challenge-response pairs (CRPs). Such primitives are desirable for applications such as communication and intellectual property protection. PUFs have been gaining considerable interest from both the academic and industrial communities because of their simplicity and stability. However, many recent studies have exposed PUFs to machine-learning (ML) modeling attacks. To improve the resilience of a system to general ML attacks instead of a specific ML technique, a common solution is to improve the complexity of the system. Structures, such as XOR-PUFs, can significantly increase the nonlinearity …

Advanced Analytics In Smart Manufacturing: Anomaly Detection Using Machine Learning Algorithms And Parallel Machine Scheduling Using A Genetic Algorithm, Meiling He

Theses and Dissertations

Industry 4.0 offers great opportunities to utilize advanced data processing tools by generating Big Data from a more connected and efficient data collection system. Making good use of data processing technologies, such as machine learning and optimization algorithms, will significantly contribute to better quality control, automation, and job scheduling in Smart Manufacturing. This research aims to develop a new machine learning algorithm for solving highly imbalanced data processing problems, implement both supervised and unsupervised machine learning auto-selection frameworks for detecting anomalies in smart manufacturing, and develop a genetic algorithm for optimizing job schedules on unrelated parallel machines. This research also …

A Deep Recurrent Neural Network With Iterative Optimization For Inverse Image Processing Applications, Masaki Ikuta

Theses and Dissertations

Many algorithms and methods have been proposed for inverse image processing applications, such as super-resolution, image de-noising, and image reconstruction, particularly with the recent surge of interest in machine learning and deep learning methods.

As for Computed Tomography (CT) image reconstruction, the most recently proposed methods are limited to image domain processing, where deep learning is used to learn the mapping between a true image data set and a noisy image data set in the image domain. While deep learning-based methods can produce higher quality images than conventional model-based algorithms, these methods have a limitation. Deep learning-based methods used in …

Transport, Photoluminescence & Photoconduction Characteristics Of Free Standing Two-Dimensional Γ-Alumina & Titanium Superlattice Doped Two-Dimensional Γ-Alumina Grown By Graphene-Assisted Atomic Layer Deposition, Elaheh Kheirandish

Theses and Dissertations

This study presents a facile high-yield bottom-up fabrication, morphology, crystallographic and optoelectronic characterization of free-standing quasi-2D γ-alumina, a non van der Waals 2D material. The synthesis comprises a multi-cycle atomic layer deposition (ALD) of amorphous alumina on a porous interconnected graphene foam as a growth scaffold and removed next by annealing and sintering the alumina/graphene/alumina sandwich at ~ 800 °C in air . The crystallographic and structural characteristics of the formed non-van der Waals quasi 2D γ-alumina were studied by X-ray diffraction (XRD), selected area electron diffraction (SAED), and high-resolution transmission electron microscopy (HRTEM). This analysis revealed the synthesized 2D …

Wound Image Classification Using Deep Convolutional Neural Networks, Behrouz Rostami

Theses and Dissertations

Artificial Intelligence (AI) includes subfields like Machine Learning (ML) and DeepLearning (DL) and discusses intelligent systems that mimic human behaviors. ML has been used in a wide range of fields. Particularly in the healthcare domain, medical images often need to be carefully processed via such operations as classification and segmentation. Unlike traditional ML methods, DL algorithms are based on deep neural networks that are trained on a large amount of labeled data to extract features without human intervention. DL algorithms have become popular and powerful in classifying and segmenting medical images in recent years. In this thesis, we shall study …

Characterization Of Fiber Bragg Grating Based, Geometry-Dependent, Magnetostrictive Composite Sensors, Edward Lynch

Theses and Dissertations

Optical sensors based on geometry dependent magnetostrictive composite, having potential applications in current sensing and magnetic field sensing are modeled and evaluated experimentally with an emphasis on their thermal immunity from thermal disturbances. Two sensor geometries composed of a fiber Bragg grating (FBG) embedded in a shaped Terfenol-D/epoxy composite material, which were previously prototyped and tested for magnetic field response, were investigated. When sensing magnetic fields or currents, the primary function of the magnetostrictive composite geometry is to modulate the magnetic flux such that a magnetostrictive strain gradient is induced on the embedded FBG. Simulations and thermal experiments reveal the …

Detection Of Stealthy False Data Injection Attacks Against State Estimation In Electric Power Grids Using Deep Learning Techniques, Qingyu Ge

Theses and Dissertations

Since communication technologies are being integrated into smart grid, its vulnerability to false data injection is increasing. State estimation is a critical component which is used for monitoring the operation of power grid. However, a tailored attack could circumvent bad data detection of the state estimation, thus disturb the stability of the grid. Such attacks are called stealthy false data injection attacks (FDIAs). This thesis proposed a prediction-based detector using deep learning techniques to detect injected measurements. The proposed detector adopts both Convolutional Neural Networks and Recurrent Neural Networks, making full use of the spatial-temporal correlations in the measurement data. …

Scatter Reduction By Exploiting Behaviour Of Convolutional Neural Networks In Frequency Domain, Carlos Ivan Jerez Gonzalez

Theses and Dissertations

In X-ray imaging, scattered radiation can produce a number of artifacts that greatly

undermine the image quality. There are hardware solutions, such as anti-scatter grids.

However, they are costly. A software-based solution is a better option because it is

cheaper and can achieve a higher scatter reduction. Most of the current software-based

approaches are model-based. The main issues with them are the lack of flexibility, expressivity, and the requirement of a model. In consideration of this, we decided to apply

Convolutional Neural Networks (CNNs), since they do not have any of the previously

mentioned issues.

In our approach we split …

Light Scattering In Diffraction Limit Infrared Imaging, Ghazal Azarfar

Theses and Dissertations

Fourier Transform Infrared (FTIR) microspectroscopy is a noninvasive technique for chemical imaging of micrometer size samples. Employing an infrared microscope, an infrared source and FTIR spectrometer coupled to a microscope with an array of detectors (128 x 128 detectors), enables collecting combined spectral and spatial information simultaneously. Wavelength dependent images are collected, that reveal biochemical signatures of disease pathology and cell cycle. Single cell biochemistry can be evaluated with this technique, since the wavelength of light is comparable to the size of the objects of interest, which leads to additional spectral and spatial effects disturb biological signatures and can confound …

Multi-Tap Extended Kalman Filter For A Periodic Waveform With Uncertain Frequency And Waveform Shape, And Data Dropouts, Justin Saboury

Theses and Dissertations

Gait analysis presents the challenge of detecting a periodic waveform in the presence of time varying frequency, amplitude, DC offset, and waveform shape, with acquisition gaps from partial occlusions. The combination of all of these components presents a formidable challenge. The Extended Kalman Filter for this system model has six states, which makes it weakly identifiable within the standard Extended Kalman Filter network. In this work, a novel robust Extended Kalman Filter-based approach is presented and evaluated for clinical use in gait analysis. The novel aspect of the proposed method is that at each sample, the present and several past …

Model Augmented Deep Neural Networks For Medical Image Reconstruction Problems, Hongquan Zuo

Theses and Dissertations

Solving an ill-posed inverse problem is difficult because it doesn't have a unique solution. In practice, for some important inverse problems, the conventional methods, e.g. ordinary least squares and iterative methods, cannot provide a good estimate. For example, for single image super-resolution and CT reconstruction, the results of these conventional methods cannot satisfy the requirements of these applications. While having more computational resources and high-quality data, researchers try to use machine-learning-based methods, especially deep learning to solve these ill-posed problems. In this dissertation, a model augmented recursive neural network is proposed as a general inverse problem method to solve these …

Novel Non-Invasive Technology For The Detection Of Thin Biofilm In Piping Systems (Phase - 1), Sachin Davis

Theses and Dissertations

Biofilms are formed when a group of cells of microorganisms stick to each other and often on a surface. The development of biofilm has been a major issue in many fields (medical field, food, chemical, and water industry are a few such fields). In the medical field alone, biofilm infections have reportedly cost over five billion USD in additional healthcare expenses. The food industry usually halts the operation of its plant eight hours, every day to ensure that their equipment and transportation channels are clean and free from any biofilm presence. Similarly, the water and chemical industry need to ensure …

Machine Intelligence For Advanced Medical Data Analysis: Manifold Learning Approach, Fereshteh S Bashiri

Theses and Dissertations

In the current work, linear and non-linear manifold learning techniques, specifically Principle Component Analysis (PCA) and Laplacian Eigenmaps, are studied in detail. Their applications in medical image and shape analysis are investigated.

In the first contribution, a manifold learning-based multi-modal image registration technique is developed, which results in a unified intensity system through intensity transformation between the reference and sensed images. The transformation eliminates intensity variations in multi-modal medical scans and hence facilitates employing well-studied mono-modal registration techniques. The method can be used for registering multi-modal images with full and partial data.

Next, a manifold learning-based scale invariant global shape …

Cad-Based Porous Scaffold Design Of Intervertebral Discs In Tissue Engineering, Ye Guo

Theses and Dissertations

With the development and maturity of three-dimensional (3D) printing technology over the past decade, 3D printing has been widely investigated and applied in the field of tissue engineering to repair damaged tissues or organs, such as muscles, skin, and bones, Although a number of automated fabrication methods have been developed to create superior bio-scaffolds with specific surface properties and porosity, the major challenges still focus on how to fabricate 3D natural biodegradable scaffolds that have tailor properties such as intricate architecture, porosity, and interconnectivity in order to provide the needed structural integrity, strength, transport, and ideal microenvironment for cell- and …

Novel Non-Invasive Technology For The Detection Of Thin Biofilm In Piping Systems (Phase - 1), Sachin Davis

Theses and Dissertations

Biofilms are formed when a group of cells of microorganisms stick to each other and often on a surface. The development of biofilm has been a major issue in many fields (medical field, food, chemical, and water industry are a few such fields). In the medical field alone, biofilm infections have reportedly cost over five billion USD in additional healthcare expenses. The food industry usually halts the operation of its plant eight hours, every day to ensure that their equipment and transportation channels are clean and free from any biofilm presence. Similarly, the water and chemical industry need to ensure …

The Design And Optimization Of Jet-In-Cross-Flow (Jicf) For Engineering Applications: Thermal Uniformity In Gas-Turbines And Cavitation Treatment In Hydro-Turbines, Tarek Mahmoud Mohammed Elgammal

Theses and Dissertations

Jet-in-cross-flow (JICF) is a well-known term in thermal flows field. Ranging from the normal phenomenon like the volcano ash and dust plumes to the designed film cooling and air fuel mixing for combustion, JICF is always studied to understand its nature at different conditions. Realizing the behavior of interacting flows and importance of many variables lead to the process of reiterating the shapes and running conditions for better outcomes or minimizing the losses. Summarizing the process under the name of optimization, two JICF applications are analyzed based on the principles of thermodynamics and fluid mechanics, then some redesigns are proposed …

Optical Fiber Communication With Vortex Modes, Du'a Al-Zaleq

Theses and Dissertations

Internet data traffic’s capacity is rapidly reaching limits imposed by optical fiber nonlinearities [5]. Optical vortices appear in high order fiber optical mode. In this thesis, we consider multimode fibers (MMFs) that are capable of transmitting a few vortex modes. Certain types of fibers have a spatial dimension leads to space-division-multiplexing (SDM), where information is transmitted with cores of multicore fibers (MCFs) or mode-division-multiplexing (MDM), where information is transmitted via different modes of multimode fibers (MMFs). SDM by employing few-mode fibers in optical networks is expected to efficiently enhance the capacity and overcome the capacity crunch owing to fast increasing …

Design And Implementation Of A Domain Specific Language For Deep Learning, Xiao Bing Huang

Theses and Dissertations

\textit {Deep Learning} (DL) has found great success in well-diversified areas such as machine vision, speech recognition, big data analysis, and multimedia understanding recently. However, the existing state-of-the-art DL frameworks, e.g. Caffe2, Theano, TensorFlow, MxNet, Torch7, and CNTK, are programming libraries with fixed user interfaces, internal representations, and execution environments. Modifying the code of DL layers or data structure is very challenging without in-depth understanding of the underlying implementation. The optimization of the code and execution in these tools is often limited and relies on the specific DL computation graph manipulation and scheduling that lack systematic and universal strategies. Furthermore, …

Analysis Of Dynamic Mode Decomposition, Archana Muniraju

Theses and Dissertations

In this master thesis, a study was conducted on a method known as Dynamic mode decomposition(DMD), an equation-free technique which does not require to know the underlying governing equations of the complex data. As a result of massive datasets from various resources, like experiments, simulation, historical records, etc. has led to an increasing demand for an efficient method for data mining and analysis techniques. The main goals of data mining are the description and prediction. Description involves finding patterns in the data and prediction involves predicting the system dynamics. An important aspect when analyzing an algorithm is testing. In this …

Design And Implementation Of A Multi-Port Solid State Transformer For Flexible Der Integration, Mohammad Rashidi

Theses and Dissertations

Conventional power system includes four major sections, bulk generation, transmission network, distribution network, and loads. The main converter in the conventional electric grid is the low-frequency passive transformer providing galvanic isolation and voltage regulation for various voltage zones. In this configuration, small-scale renewable energy resources are generally connected to the power system at low voltage zones or inside microgrids.

Recent developments in the design of power electronic elements with higher voltage and power ratings and medium/high frequency enable making use of solid state transformer at different voltage levels in the distribution system and microgrid design. In this work, the concept …

Threshold Free Detection Of Elliptical Landmarks Using Machine Learning, Lifan Zhang

Theses and Dissertations

Elliptical shape detection is widely used in practical applications. Nearly all classical ellipse detection algorithms require some form of threshold, which can be a major cause of detection failure, especially in the challenging case of Moire Phase Tracking (MPT) target images. To meet the challenge, a threshold free detection algorithm for elliptical landmarks is proposed in this thesis. The proposed Aligned Gradient and Unaligned Gradient (AGUG) algorithm is a Support Vector Machine (SVM)-based classification algorithm, original features are extracted from the gradient information corresponding to the sampled pixels. with proper selection of features, the proposed algorithm has a high accuracy …

Bayesian Methods And Machine Learning For Processing Text And Image Data, Yingying Gu

Theses and Dissertations

Classification/clustering is an important class of unstructured data processing problems. The classification (supervised, semi-supervised and unsupervised) aims to discover the clusters and group the similar data into categories for information organization and knowledge discovery. My work focuses on using the Bayesian methods and machine learning techniques to classify the free-text and image data, and address how to overcome the limitations of the traditional methods. The Bayesian approach provides a way to allow using more variations(numerical or categorical), and estimate the probabilities instead of explicit rules, which will benefit in the ambiguous cases. The MAP(maximum a posterior) estimation is used to …

An Energy Efficient, Load Balancing, And Reliable Routing Protocol For Wireless Sensor Networks, Kamil Samara

Theses and Dissertations

AN ENERGY EFFICIENT, LOAD BALANCING, AND RELIABLE ROUTING PROTOCOL FOR WIRELESS SENSOR NETWORKS

by

Kamil Samara

The University of Wisconsin-Milwaukee, 2016

Under the Supervision of Professor Hossein Hosseini

The Internet of Things (IoT) is shaping the future of Computer Networks and Computing in general, and it is gaining ground very rapidly. The whole idea has originated from the pervasive presence of a variety of things or objects equipped with the internet connectivity. These devices are becoming cheap and ubiquitous, at the same time more powerful and smaller with a variety of onboard sensors. All these factors with the availability of …

Transient Control Of Synchronous Machine Active And Reactive Power In Micro-Grid Power Systems, Luke Gerard Weber

Theses and Dissertations

There are two main topics associated with this dissertation. The first is to investigate

phase–to–neutral fault current magnitude occurring in generators with multiple zero–sequence

current sources. The second is to design, model, and tune a linear control system for oper-

ating a micro–grid in the event of a separation from the electric power system.

In the former case, detailed generator, AC8B excitation system, and four–wire electric

power system models are constructed. Where available, manufacturers data is used to

validate the generator and exciter models. A gain–delay with frequency droop control

is used to model an internal combustion engine and governor. …

A New Paradigm Of Maximizing The Wind And Solar Penetration– A Economical Assessment, Yuming Chen

Theses and Dissertations

Wind and solar energies are the most potential and widely-used renewable energies. But in most cases these energies cannot be maximized because of transmission line capacity and their remote location. Therefore, this thesis proposes a new paradigm which using battery transportation and logistics instead of transmission line, to maximize wind and solar energies. The main focus of this work is to investigate the economical feasibilities of this new paradigm.

In the first part, different models and application are presented. The purpose is finding an appropriate model which can make full use of existing grid resources such as transmission line and …

The Effects Of Geomagnetic Disturbances On Electrical Power Systems, Benjamin J. Hynes

Theses and Dissertations

Solar storms that generate coronal mass ejections are a cause for concern due to the damage that they cause in high voltage power grids. Geomagnetically induced currents can be introduced onto the grid and cause many adverse effects. The vulnerability of the bulk electric power systems to such events has increased during the past few decades because the power system transmission lines have become more interconnected and have increased in length. Real and reactive power flows, voltage fluctuations, frequency shifts, undesired relay operations, higher order harmonic currents, undesired damage to assets and failure of assets are all possible outcomes from …

Design And Optimization Of Hybrid Energy Storage For Photovoltaic Power Fluctuation Smoothing Based On Frequency Analysis, Ruirui Yang

Theses and Dissertations

A proper design of energy storage system (ESS) can effectively smooth the photovoltaic (PV) output power fluctuation, lower the cost, and improve the power quality and stability.

According to the response characteristics of different energy storage equipment, an optimal hybrid EES sizing method is proposed based on frequency analysis. A hybrid ESS including lead-acid battery, lithium battery and electric double-layer capacitor (EDLC) is selected to smooth out PV power fluctuation and meet both power and energy requirement of the power grid. Fast Fourier Transform (FFT) method is applied for analyzing the spectrum of unwanted PV fluctuation. From the FFT analysis, …

Water Withdrawal And Consumption Reduction Analysis For Electrical Energy Generation System, Narjes Nouri

Theses and Dissertations

There is an increasing concern over shrinking water resources. Water use in the energy sector primarily occurs in electricity generation. Anticipating scarcer supplies, the value of water is undoubtedly on the rise and design, implementation, and utilization of water saving mechanisms in energy generation systems are becoming inevitable. Most power plants generate power by boiling water to produce steam to spin electricity-generating turbines. Large quantities of water are often used to cool the steam in these plants. As a consequence, most fossil-based power plants in addition to consuming water, impact the water resources by raising the temperature of water withdrawn …

Virtual Droop Control Framework And Stability Analyses For Microgrids With High Penetration Of Renewables, Ashishkumar Kanubhai Solanki

Theses and Dissertations

Microgrids can provide the most promising means of integrating large amounts of distributed sources into the power grid and can supply reliable power to critical loads. However, managing distributed sources and loads within a microgrid during island and grid-tie modes and during transitions is a challenge. Stable operation of a microgrid is a concern specifically during the starting of motor loads, switching of large loads, and in presence of high penetration of renewable resources. Hence, a generalized control framework is required to regulate microgrid voltage and frequency, maintain power quality, manage Distributed Generations (DG) and ensure microgrid stability. Several control …