Engineering Commons^™

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 …

An Insurance Framework For Cyber-Physical Power Systems Considering Integrated Cybersecurity-Reliability Assessment, Pikkin Lau

Theses and Dissertations

Due to the development of cyber-physical systems for modernizing power grids, vulnerabilityassessment has become an emerging focus in power system security studies. With the increasing application of cyber-enabled technologies in power systems, modern power system is prevalently exposed to a wide gamut of cybersecurity threats. In this dissertation, the power supply reliability is evaluated considering the strategic allocation of defense resources and smart technologies. The optimal mixed strategies are formulated by the Stackelberg Security Game to allocate the defense resources on multiple targets subject to cyberattacks. Smart monitoring with preventive and corrective measures is able to boost the substation availability …

A High-Bandwidth, Spectrally Broad Photodetector Based On Optically-Induced Seebeck Effect, Niloufar Yavarishad

Theses and Dissertations

In this thesis, we engineered a fast response high bandwidth self-powered infrared photodetector based on optically induced Seebeck effect in Cd3As2 operating at room temperature. The metal-semimetal-metal device was subject to transient photo-response tests using high-frequency lock-in modulation techniques. Our photodetector demonstrates a Seebeck voltage under the off-center illumination of a laser with the wavelength of 1064 nm, due to a temperature gradient. The photocurrent is readily registered at a modulation frequency of 6 kHz and further analysis indicates the sensor intrinsic bandwidth is predicted to approach the terahertz range. The responsivity of the sensor is 0.27 mA/W at room …

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 …

Modular Multilevel Converters With Module-Level Energy Storage For Medium Voltage Applications, Bora Novakovic

Theses and Dissertations

This dissertation is on Modular Multilevel Converter (MMC) converter design and analysis and its integration with energy storage at the low voltage module-level. The developed converter concept and topology can be used in various applications especially for the support of intermittent renewable energy resources. The general converter structure is analyzed and extended to include integrated energy storage suitable but not limited to medium voltage applications. The behavior of the idealized structure is analyzed to obtain equations that govern general converter behavior and identify possible control loops. Detail mathematical switching model is developed for the MMC converter with generalized module structure. …

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 …

Real Time License Plate Detection Based On Machine Learning, Yu-Liang Chiang

Theses and Dissertations

License Plate Recognition (LPR) is a very useful technology skill for our world, and also includes a wide range of applications. During my student life in the US, it is not common to see this kind of technology applied in the public parking lot. LPR has been researched for many years in Asia. There are a lot of LPR systems, which include different types of technologies, being used in Taiwan. In my point of view, those systems are still using the conventional technology, which does not involve artificial intelligence. In many applications, that makes it possible to make mistakes in …

Design And Optimization Of A Modular Dc-Dc Power Converter For Medium Voltage Shipboard Applications, Seyed Rasoul Hosseini

Theses and Dissertations

Power electronic converters rated for medium voltage direct current (MVDC) are promising for electrification of future ships. In shipboard electrification, due to limitation of space, energy and technical maintenance, the high-power density, high efficiency and modularity of the power electronic converters are desired. Utilizing power modules made from wide band gap (WBG) semiconductors like silicon carbide (SiC) and high frequency power transformer (HFPT) can be beneficial for obtaining the high-power density, high efficiency and isolation that is required for the power electronic converters. To provide power for the low voltage (LV) DC loads, a conversion of the power from MVDC …

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 …

Design And Analysis Of Fully-Electronic Magnet-Free Non-Reciprocal Metamaterial, Swadesh Poddar

Theses and Dissertations

Reciprocity is a fundamental and very important characteristics of the vast majority of electronic devices, and requires that signals travel in both forward and reverse directions in the same manner. Similarly, electromagnetic non-reciprocity or one way wave propagation, implies that the field created by a source at an observation point is not the same when source and observation points are interchanged. Non-reciprocal devices such as isolators, circulators, phase shifters, polarizers,

switches, tunable resonators, tunable filters, and gyrators enable new applications from radio frequencies to optical frequencies. However, non-reciprocity has been implemented in the past using ferrites in the presence of …

Graphical Convolution Network Based Semi-Supervised Methods For Detecting Pmu Data Manipulation Attacks, Wenyu Wang

Theses and Dissertations

With the integration of information and communications technologies (ICTs) into the power grid, electricity infrastructures are gradually transformed towards smart grid and power systems become more open to and accessible from outside networks. With ubiquitous sensors, computers and communication networks, modern power systems have become complicated cyber-physical systems. The cyber security issues and the impact of potential attacks on the smart grid have become an important issue. Among these attacks, false data injection attack (FDIA) becomes a growing concern because of its varied types and impacts. Several detection algorithms have been developed in the last few years, which were model-based, …

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. …

Health Condition Assessment Of Multi-Chip Igbt Module With Magnetic Flux Density, Xueni Ding

Theses and Dissertations

To achieve efficient conversion and flexible control of electronic energy, insulated gate bipolar transistor (IGBT) power modules as the dominant power semiconductor devices are increasingly applied in many areas such as electric drives, hybrid electric vehicles, railways, and renewable energy systems. It is known that IGBTs are the most vulnerable components in power converter systems. To achieve high power density and high current capability, several IGBT chips are connected in parallel as a multi-chip IGBT module, which makes the power modules less reliable due to a more complex structure. The lowered reliability of IGBT modules will not only cause safety …

Modulation And Control Techniques For Performance Improvement Of Micro Grid Tie Inverters, Zeljko Jankovic

Theses and Dissertations

The concept of microgrids is a new building block of smart grid that acts as a single controllable entity which allows reliable interconnection of distributed energy resources and loads and provides alternative way of their integration into power system. Due to its specifics, microgrids require different control strategies and dynamics of regulation as compared to ones used in conventional utility grids. All types of power converters used in microgrid share commonalities which potentially affect high frequency modes of microgrid in same manner. There are numerous unique design requirements imposed on microgrid tie inverters, which are dictated by the nature of …

A Hardware-In-The-Loop Platform For Dc Protection, Mark Vygoder

Theses and Dissertations

With the proliferation of power electronics, dc-based power distribution systems can be realized; however, dc electrical protection remains a significant barrier to mass implementation dc power distribution. Controller Hardware-in-the-loop (CHiL) simulation enables moving up technology readiness levels (TRL) quickly. This work presents an end-to-end solution for dc protection CHiL for early design exploration and verification for dc protection, allowing for the rapid development of dc protection schemes for both Line-to-Line (LL) and Line-to-Ground (LG) faults. The approach combines using Latency Based Linear Multistep Compound (LB-LMC), a real-time simulation method for power electronic, and National Instruments (NI) FPGA hardware to enable …

Quantitative Optical Imaging Of Metabolic And Structural Biomarkers In Rodent Injury Models, Shima Mehrvar

Theses and Dissertations

The assessment of organ metabolic function using optical imaging techniques is an overgrowing field of disease diagnosis. The broad research objective of my PhD thesis is to detect quantitative biomarkers by developing and applying optical imaging and image processing tools to animal models of human diseases. To achieve this goal, I have designed and implemented an optical imaging instrument called in vivo fluorescence imager to study wound healing progress. I have also developed a 3-dimensional (3D) vascular segmentation technique that uses intrinsic fluorescence images of whole organs.

Intrinsic fluorophores (autofluorescence signals) provide information about the status of cellular bioenergetics in …

Medical Image Segmentation With Deep Learning, Chuanbo Wang

Theses and Dissertations

Medical imaging is the technique and process of creating visual representations of the body of a patient for clinical analysis and medical intervention. Healthcare professionals rely heavily on medical images and image documentation for proper diagnosis and treatment. However, manual interpretation and analysis of medical images is time-consuming, and inaccurate when the interpreter is not well-trained. Fully automatic segmentation of the region of interest from medical images have been researched for years to enhance the efficiency and accuracy of understanding such images. With the advance of deep learning, various neural network models have gained great success in semantic segmentation and …

Power Electronic Architecture For Multi-Vehicle Extreme Fast Charging Stations, Nicholas Hoeft

Theses and Dissertations

Electric vehicles (EV) are quickly gaining popularity but limited driving range and a lack of fast charging infrastructure are preventing widespread use when compared with gas powered vehicles. This gave rise to the concept of multi-vehicle extreme fast charging (XFC) stations. Extreme fast charging imposes challenges in the forms of power delivery, battery management, and energy dispatch. The extreme load demand must be handled in such a way that users may receive a timely charge with minimal impacts on the electric grid. Power electronics are implemented to address these challenges with highly power dense and efficient solutions. This work explores …

Assessment Of Sensory Abnormalities In Children With Asd Using Virtual Reality, Ankit Koirala

Theses and Dissertations

Sensory abnormality is one of the important characteristics of Autism Spectrum Disorder(ASD). A large number of studies suggest a strong connection between sensory abnormalities and ASD. Therefore, it is important to assess sensory abnormalities for diagnosis and intervention of ASD. In this thesis study, we aim to develop a virtual reality system that can measure sensory abnormalities in adolescents with ASD. Sensory abnormalities can affect all five senses: touch, vision, smell, taste and auditory. However, in this study, we focus on assessing sensory abnormality in vision and touch sensory processing. Twelve adolescents with ASD and 12 typically developing (TD) adolescents …

Vehicle Interior Access Deployable Worksurface Mechanism Concept Product Design, Premchand Gunachandran

Theses and Dissertations

by

Premchand Gunachandran

The University of Wisconsin-Milwaukee, 2019

Under the Supervision of Professor Mohammad Habibur Rahman

Easy access and adjusting the vehicle interior configuration to a variety of situations and uses is the general desire for any vehicle user. To meet such desire an attempt has been made in this study to conceptualize a design to develop a new mechatronic product called re-configurable vehicle interior console mechanism to deploy a worksurface (DWS), which will provide flexible use of the vehicle’s interior of both partial and fully autonomous vehicles. This re-configurable vehicle interior console will deploy the DWS using a power …

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 …

Cavity Environmental Control System Upgrade For Nasa’S Stratospheric Observatory For Infrared Astronomy, Ashraf Al-Hajjeh

Theses and Dissertations

The main goal of this project is to fulfill the need of a controller upgrade for the Cavity Environmental Control System (CECS) on NASA’s Stratospheric Observatory for Infrared Astronomy (SOFIA) aircraft. The preceding controller had multiple disadvantages including operating in an unpressurized region, incomplete functionality implementation, limited fault and status monitoring capability, and reduced maintainability and reliability. The new controller will go through the NASA design process to fulfill all the requirements of CECS operation including complete functionality of all devices currently installed on the aircraft, added devices to improve fault and health monitoring, and overall improvement in maintainability and …

Exploring Methods For Studying Recoverability Of Shipboard Electrical Power Distribution Systems, Jacob David Gudex

Theses and Dissertations

Advancement of the technology included on ships, is changing the nature of loads installed on ships. Not only are there more loads than installed power generation, but advanced electrically powered weapons and sensors are changing the profile of the installed loads. These are challenges for future shipboard power systems design. Challenges which must be solved with careful distribution system planning, energy storage integration, and selection of individual power electronic converters within the ship. Different topologies and distribution systems have differing fault isolation and recovery (FIR) capability sets, which affects ship survivability. Furthermore, different FIR capability sets, operate at different speeds. …

Advanced Metering Infrastructure Security With Software-Defined Network In Smart Grid, Yi-Chen Chung

Theses and Dissertations

The Advanced Metering Infrastructure (AMI) is the most important and basic element in the Smart Grid systems. Technologies grow complicated as the world becomes more convenient. Power grid, smart building, electric vehicles, and other technology need to be managed and maintained flawlessly in case of the possibility of cyberattacks to shut down all the systems and result in huge loss economically or potentially affect people's life. It is important to use communication technologies to provide many functions including facilitate bidirectional communications and remote controls. Since AMI needs to be widely deployed to each home user, power companies are required to …

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 …

Sensing With Geometry-Dependent Magnetostriction Via An Embedded Fiber Bragg Grating, David Frailey

Theses and Dissertations

Fiber optic current sensors (FOCSs) have unique advantages in electromagnetic interference

immunity and direct current measurements. Here, magnetostrictive composites and

their interactions with embedded ber Bragg gratings (FBG) were explored to form novel

FOCSs with predictable and temperature-independent sensitivity. Magnetostrictive, particularly

Terfenol-D/epoxy, composites maintain the mangetostrictive expansion under an

external magnetic eld while gaining

exibility in engineering. In contrast to ordinary strain

gauges, an embedded FBG can provide an optical signal inferring simultaneously a strain

and its gradient inside a composite. In principle, the sensing of strain gradient is thermally

independent. Creating appropriate geometries for magnetostrictive composites enables the

conversion …

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 …

Financially Motivated Lmp Manipulation By Aggregators In Power Markets, Chaoyi Chen

Theses and Dissertations

Renewable energy accounts for a sizeable share within modern power systems and aggregators of renewable generators play an important role in the electricity market. However, because renewable generators produce power intermittently, it is hard to monitor and supervise the behavior of the aggregators. There is a chance for aggregators to manipulate the locational marginal prices (LMPs) in the power market by curtailing generation in order to increase their profits.

In this thesis we propose a tri-level model that can quantify aggregators’ potential profits. This model is based on both a real-time optimal dispatch and an LMP clearing procedure. With this …

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 …

A Fault-Tolerant Control Strategy For Three-Level Neutral-Point Clamped (Npc) Inverter, Weijun Zhu

Theses and Dissertations

When the open-circuit fault occurs on neutral-point clamped (NPC) inverters, it can cause the distortion of output currents, excessively large fluctuation of output voltages, and unbalanced neutral-point potential. Currently, several existing fault diagnosis methods are able to identify the fault types, but they are unable to identify the switching devices where the open-circuit faults occur. Furthermore, even if the open-circuit faults can be identified, the implications caused by open-circuit faults need to be further addressed. This thesis is focused on diagnosing the open-circuit faults and mitigating the problems caused by these faults.

An effective fault diagnosis method is proposed in …