Industry-Sponsored Student Capstone Projects
2023/2024
In the 2023/24 academic year, the industry capstone program was supported by 54 sponsors, more than half of which were returning, and 95 real-world projects. Over 550 students from across the College of Engineering participated. Scroll down to learn more about each project.The Boeing Company
Composite Stop Beam Design
This student team was provided with a generic/non-proprietary stop fitting shape representing one end of a passenger entry door stop beam. The student team was asked to create 3 stop beams using different composite manufacturing methods, which could include hand layup, chopped fiber, oriented fiber tows, 3D printed continuous carbon fibers, resin transfer molding, or similar. This student team was tasked with comparing the composite parts to an aluminum baseline part (that they fabricate). This student team worked to explore novel fabrication techniques for stop fittings and to compare fabrication techniques to better understand the strengths and weaknesses of the fabrication techniques. This student team worked to test each part to failure and compare their results. The student team worked to provide a test report detailing their findings of which composite manufacturing technology provided the strongest stop beam element. The student team worked to compare the stop beam to an aluminum baseline part and to describe the pros and cons of each material system.
![](https://www.engr.washington.edu/industry/capstone-projects/images/Boeing Bondline Thickness Team Photo-667d8997d3905.png)
The Boeing Company
Effect of Bondline Thickness on Mechanical Performance of Adhesive Bonds
Adhesive bonding systems consist of four critical elements: substrate material, adhesive material, surface preparation, and bonding/cure process. The adhesive bond performance is optimal within a thickness range, dependent on the specific adhesive and cure process. There is growing interest in understanding the effect of varying the bondline thickness of film (or paste) adhesives on mechanical performance to determine appropriate bondline thickness limits. In addition, there is interest in understanding which adhesive bond performance test methods are useful for assessing bondline thickness effects. This student team will work toward two objectives: (1) determine an appropriate bonding system with given substrate and film or paste adhesive composite materials and (2) characterize mechanical performance dependence on bondline thickness. To meet these objectives, this student team will work to: 1. Propose a suitable secondary bonding system cure process and surface preparation for given substrate and adhesive composite materials, ensuring bonding system achieves cohesive failure within adhesive. 2. Propose a suitable method for controlling bondline thickness within bonding system. 3. Propose an appropriate test plan/DOE plan for typical structural tests of adhesive bond performance. Design and develop test coupons with varying bondline thickness for comparison. 4. Perform mechanical tests. Characterize variable bondline thickness with respect to mechanical performance. 5. Publish results of tests - conclusions and recommendations. This student team will work to create a technical summary report on findings of testing.
![](https://www.engr.washington.edu/industry/capstone-projects/images/Boeing Evaluation of Plasma Team Photo-667d89ff7d284.png)
The Boeing Company
Evaluation of Plasma Treatment Detection Methods for Thermoplastic Substrates
Atmospheric plasma has been shown to activate inert bonding surfaces, such as thermoplastic substrates. Structural repair of thermoplastic substrates requires specific plasma treatment parameters to be employed - power, number of passes, speed of a pass, and stand-off distance between substrate and the plasma source. To the naked eye, a machined thermoplastic composite surface that is plasma treated appears no different from one that is not treated. This creates a challenge confirming whether the surface was adequately treated or not. There exist potential detection methods for determining whether plasma treatment was adequately performed. This student team will work to identify potential non-contact and contact methods to detect plasma treatment and then characterize the effect of those methods, such as potentially contaminating the surface, on bond quality. To achieve this objective, this student team will work to identify and evaluate the relative effects of plasma detection methods on bond quality of machined thermoplastic (TP) substrates, by performing the following: 1. Literature survey and selection of non-contact and contact methods for detecting plasma surface treatment. 2. Design of Experiments (DoE) methodology to establish the optimum test matrix - evaluate effectiveness of detection method(s) and the effect of the detection method(s) on bond quality 3. Perform Double Cantilever Beam (DCB) testing per ASTM D5528 (Mode 1 Interlaminar Fracture Toughness test) **Obtain or fabricate substrate test coupons using carbon reinforced thermoplastic (TP) materials **Obtain or fabricate repair test coupons using carbon reinforced thermoset material **Plasma Treat TP coupons per standard approved treatment parameters (to be provided by Boeing) using robot or mechanical fixture controlled plasma heads. **Subject some plasma treated TP coupons to plasma detection method(s) **Apply mitigation techniques to remove any potential contamination **Bond DCB coupons (TP coupons bonded to thermoset coupons) per standard process using adhesive and perform DCB tests 4. Document test report Boeing designs capstone projects to be multi-disciplinary, encouraging engagement of students with diverse backgrounds and use of universal design principles. Mentors will offer students opportunities to expand their skill set beyond university education. Boeing is a global corporation and these projects enable maturation of technologies that benefit our diverse global market.
The Boeing Company
Formula Motor Sports Car Improved Part Design, Material and Fabrication Techniques
This student team worked to identify an application that would improve performance, improve quality, lower cost, and/or a shorten lead time for parts on a formula style race car. To accomplish this, this student team worked to learn about different materials, processes and fabrication techniques applied to parts designed for a formula style race car, and select the optimal materials to design the part(s) with. The student team also worked to define testing requirements, build the part(s) for installation, and analyzed and tested (as needed) on the formula style race car to validate that the part(s) was/were suitable for use on the car and for design optimization. The student team also worked to finalize the design and load/strength requirements and refine the current design to ensure it would function properly and was safe for use on the race car. Finally, the student team worked to complete a report documenting the analysis and design building and testing process and results.
![](https://www.engr.washington.edu/industry/capstone-projects/images/Boeing Laser Team Photo-667d8a982028b.png)
The Boeing Company
Laser Surface Smoothing Optimization
Laser processing of substrates is an evolving technology that offers advantages in processing rate, sustainability and ergonomics. As laser capabilities ramp up, the characterization of more material systems is required to expand the scope of opportunities. This student team will work to evaluate the effectiveness of lasers to remove material from a polymeric surface to yield a smooth, uniform surface, as an alternative to sanding. (Sanding is used to smooth surfaces for many end-item applications, ranging from decorative laminates, to decorative paint finishes.) To date, the laser has been used to remove a given amount of a material, but follows the contour of the underlying surface. The objective this student team will work to accomplish is to determine the effectiveness of laser processing for near surface ablation and smoothing of material in terms of rate and uniformity. The materials this student team could potentially use can be either 3D printed (FDM) materials with characteristic, repeated surface roughness from the resolution of the layer height or other relevant polymer based composite systems. First, the student team will work to analyze the untreated surface for surface topography and surface energy analysis. The student team will also work to design a laser ablation test to determine the effectiveness of the laser to remove material. Third, the student team will work to develop a rate of removal program that can be tuned to the topology of the surface. And then, the student team will work to tune the laser program to smooth the surface to a consistent profile. Following this, the student team will work to characterize the material for the effectiveness at smoothing the surface. The questions this student team will work to answer include: what are the material properties of the exposed substrate? When comparing the surface energy and adhesive properties of the material to the control specimens, what is the effect of too little power and too much power delivered? This student team could work to test on various grades of materials (such as high temperature thermoplastics like PEEK or PEKK or Onyx, common low-grade polymers like ABS or PLA or ASA, bagside composite, etc.). The student team will work to develop laser delivery settings that are appropriate for each class of materials for surface smoothing. The student team will work to record the test results of the of the methods performed. Provide a report out of the approach, techniques attempted, results and conclusions. Last, the student team will work to provide a future work statement based upon the conclusions drawn.
The Boeing Company
Light - Quantum Emitter Interaction Modeling
This student team worked to analyze the fundamentals of light interaction with a quantum emitter in support of quantum sensing, communication and electronics control design concepts under consideration at Boeing. The students worked to define, model and solve increasingly complex and physically accurate quantum mechanical systems relevant to these technological areas. The Project Mentor provided initial models and propose solution methodologies, and the students worked to seek alternative methods and additional topics of interest to apply to problem solving. Motivations of this project were to: (1) advance existing and (2) seek alternative modeling and solution methods to apply to Boeing's quantum projects; (3) encourage potential future Boeing employees to develop quantum technological, mathematical and computational skills. This student team began the project with analysis of the Jaynes-Cummings model, which in its simplest form describes the interaction of a single photon mode (plane wave) with a two-energy level quantum emitter (such as an atom). One example of interest to Boeing was Photon Addition, where an excited emitter transitions from its higher energy level to lower energy level while interacting with an incident "signal" photon, thus emitting an additional photon that may carry some of the characteristics of the incident photon, thus amplifying the signal, improving its detection and measure, and increasing its signal-to-noise ratio in a quasi-noiseless manner surpassing classical statistics. The quantum system would then be incrementally expanded to include multiple photon modes interacting with one or more physically realizable emitters with multiple energy level transitions. As later stage of the project, the student team worked to expand to interaction with entangled photons and analysis and solution of the Master's Equation, which describes the aforementioned light-emitter interaction as well as interaction with the environment and inclusion of even more physical realism of the quantum emitter characteristics and performance, relevant to existing or potential quantum emitters under development. Examples of quantum emitters that the student team considered to be physically characterized in the models include: trapped atoms, solid state emitters such as Nitrogen vacancy centers and hexagonal Boron Nitride, and quantum dots. The student team worked to develop analytical and numerical techniques to efficiently solve these systems, and worked to evaluate performance of the models through simulation of physical measurements as they relate to examination of spontaneous vs. stimulated emission, increase in signal-to-noise ratio, and amplification of information encoded in the photon signal (such as polarization, phase, etc.) A desired outcome this student team worked toward was to develop efficient numerical methodologies to model and evaluate the performance of light-emitter interaction design concepts. The student team worked to use the models, with increasingly complex systems of multiple photon modes and multiple energy level emitters, to compare and differentiate various quantum emitter systems and evaluate their performance in increasing the sensitivity of photon signal detection and measurement, increasing range and resolution of quantum imaging systems, evaluating quantum communication concepts. The student team worked to deliver reports and presentations of the incrementally complex light-matter interaction models and their solutions, analytical and numerical algorithms for solving the models, and suggestions for future advancement of these techniques that could lead to additional research projects.
The Boeing Company
Natural Fiber Composites
This student team will work to fabricate natural fiber composite systems from a down-selected polymer matrix with an appropriate test plan to evaluate mechanical performance. The composite system will be composed of reinforcing fibers sourced from plant matter or renewable material with a polymer matrix of either thermoplastic or thermoset polymer. Each panel will be fabricated in a similar process with option to adjust process for optimization. Panel and coupon fabrication will be accompanied by an appropriate test plan to evaluate mechanical performance and compare to existing fiber-reinforced plastic (FRP) composite systems. This student team will work to include evaluation and comparison of handling materials during panel fabrication, defect formation in cured panels, ease of coupon fabrication, and mechanical properties data for use of potentially less environmentally impactful materials due to the renewable nature of the fiber sources. Students with knowledge on composite fabrication (to help with making the materials needed to be tested) and with interests in performing mechanical tests and interpreting results are encouraged to apply.
![](https://www.engr.washington.edu/industry/capstone-projects/images/Boeing_SustainabilityProject_ASOT-6670a17e94ac4.jpeg)
The Boeing Company
Sustainable Airport Operations
A number of international and regional airlines have started to utilize zero emission vehicles (ZEV) as part of their ground support operations. Numerous technical, logistic, and financial challenges have prevented the widespread adoption across the breath of airports and airlines. This student team will work to create a plan to utilize zero emission vehicles (ZEV) for ground support equipment for an airline at a local commercial airport (i.e. Seattle-Tacoma, Paine Field, Spokane, etc.). This student team will work to apply their knowledge of sustainable transportation, traffic optimization, and infrastructure to identify and mitigate challenges for sustainable airport ground operations. This student team will work to create a final report that will serve as a guide for implementation. This student team will work to provide a final deliverable detailing the utilization plan, risks, and estimated Ozone reduction. The student team should work to include in their report discussions about methods, assumptions, conclusions, and areas for further consideration. This student team will work to provide a final deliverable including the details of the utilization plan, risks, and estimated Ozone reduction. This student team will work to define the vehicles needed to support airline ground operations and the infrastructure needed to support both conventional and zero emission vehicles (ZEV) for comparison - scalable for size. ZEVs can be electric, hydrogen, or a combination. Other details the student team will work to take into consideration (although not limited to the following) include: charge/refuel times, ZEV mileage, availability rate and time.
The Boeing Company
Sustainable Surface Layer Removal to Enable Recycling
Usage of carbon fiber composites in airplanes improves product sustainability by increasing durability, reducing weight, enabling part life extension, and improving producibility. However, the disposal of end-of-service composites has emerged as a pressing environmental challenge. While there are methods to recycle the carbon fiber reinforced polymer material by itself, current technology gaps prevent recycling feasibility of the end-of-service mixed material. One of the challenges hindering the effectiveness of recycling processes is the presence of surface layers, such as coatings and adhesives. This student team will work to conduct research, identify potentially efficient methods, and experiment with those methods (time and lab resources permitting) for the removal of process-limiting surface layers during end-of-life carbon fiber recycling. The objectives this student team will work to accomplish include: identifying and exploring innovative techniques that can safely and efficiently remove these surface layers, enabling enhanced recycling efficiency and promoting sustainable practices. Additionally, this student team will work to identify potential use cases for the byproducts generated from surface layer removal, thus promoting the circular economy. The outcomes this student team is working toward will potentially contribute to enhanced recycling efficiency, sustainability, and overall reduction of the environmental impact associated with end-of-life carbon fiber composites. This student team will work to address the following research questions: 1. What are the different types of surface layers commonly found on end-of-life carbon fiber composites? 2. How could these surface layers impact the efficiency of existing carbon fiber recycling processes? 3. What are the existing methods and techniques used for removal of similar finishes and surface layers during production, maintenance or other recycling industries? 4. Can novel approaches be developed or adapted from question 3 to improve the efficiency and effectiveness of surface layer removal? 5. How can the removed surface layers be properly handled, reused, recycled, or safely disposed? Methodology: 1) This student team will work to conduct a literature review and available case study Analysis. The student team will work to conduct an extensive review of existing literature and research papers to gather insights into the types and characteristics of surface layers, their impact on recycling, and existing removal methods. Additionally, this student team will work to review case studies of existing recycling facilities to gather real-world data on the effectiveness of current surface layer removal techniques. 2) This student team will work to collect expert interviews and surveys. This student team will work to interview industry experts and stakeholders internal to Boeing and throughout supply chain collecting insights and inputs to further advise characterization, process availability, existing removal methods, etc. This student team will also work to design and administer surveys to gather data from industry experts, researchers, and recycling practitioners to understand their experiences, challenges, and insights related to surface layer removal in [carbon fiber or related] recycling. 3. This student team will work to generate a research report. This student team will work to provide a summarized research report of the literature review, case studies, expert interviews and surveys. 4. This student team will work to provide experimental analysis. This student team will work to develop and execute a series of experiments to evaluate the efficiency of different removal techniques, potentially including but not limited to mechanical, chemical, and thermal methods, for identified types of surface layers. This student team will also work to collect and characterize outputs including gases and solid byproducts. 5. This student team will work to provide comparative analysis and sustainability considerations. This student team will work to analyze the results of the experiments, comparing the effectiveness, efficiency, and environmental impact of the different removal techniques. This student team will also work to propose possible alternative use cases for byproduct materials. 6. This student team will work to provide an experimental Report. Based on experimental findings the student team will work to achieve, this student team will work to identify methods most viable and compatible with end of service carbon fiber recycling. Propose potential modifications or improvements to existing techniques or opportunistic novel approaches for efficient surface layer removal. This student team will work to provide a report of all testing and findings. Desired outcomes this student team should work to accomplish include: 1. Identification and characterization of the common types of surface layers present on end-of-life carbon fiber composites. 2. Evaluation of the impact of surface layers on the efficiency of the carbon fiber recycling process. 3. Comparison of existing removal techniques and their effectiveness for different types of surface layers. 4. Recommendation of adapted optimized or novel methods for efficient removal of process limiting surface layers. Identify byproducts 5. Characterize the removed surface layer byproducts and provide recommendations of their potential use cases or sustainable and safe disposal. 6. Two reports – midterm research summary and final experimental summary detailed above.
The Boeing Company
Validation of Methods for Analyzing Synthetic Fuels
In 2022 - 2023, a capstone project was conducted called "Methods of Analyzing Synthetic Fuels on Board for Data Collection and Indication" led by Dr. Ben Rutz. The team identified several avenues for measuring density, height, and hydrocarbon composition; however, due to time constraints they were not able to test, validate or build upon the initial proposals. The 2023-24 student team (this year's team) will work to assess and improve upon the proposals generated by the previous team, then build and execute a system to test and validate these methods in both ground and altitude simulated environments. This student team could potentially re-use and improve upon the equipment procured during the project year 2022 - 2023. This student team will work within the following project perimeters: 1. The tolerance of all properties shall be +/- 1% 2. Capacitance and speed-of-sound methods to measure properties should not be considered as part of this study. 3. Assume no fuel additives are present per the ASTM D7566 & ASTM D1655 standards. It is ok to propose adding additives if this is supports your method of measurement and analysis. 4. Minimal weight and minimal-to-no electricity in the tank are important design and safety parameters. 5. GCxGC should not be considered as a method for measuring hydrocarbon distribution This student team will work to achieve a working system that tests and validates the proposed methods for analyzing synthetic fuels to measure: Density and Fuel Height with a stretch goal of identifying and validating a new method to determine the hydrocarbon distribution. This student will work to complete a report that identifies areas to consider to adapt this system or method for commercial economical use.
University of Alaska - Alaska Center for Energy and Power
Efficient Energy Research: Building an Advanced Language Model and Interface
This student team will work to develop a robust Large Language Model (LLM) capable of analyzing energy-related documents. The LLM the student team works to create will extract valuable insights from energy-related PDFs, perform labeling and cleaning tasks, and provide researchers with actionable information. Additionally, this student team will work to create a user-friendly web application to facilitate researchers' access to the LLM's capabilities. Energy researchers often struggle to unearth pertinent information from a multitude of documents. This student team will work to streamline their efforts by deploying an advanced LLM, alleviating the data discovery challenge. The student team's goal extends beyond the University of Alaska – it envisions an open source solution that benefits multiple universities, reinforcing collaborative knowledge sharing. Successful project completion holds the potential to streamline energy research by providing rapid data analysis. The project stands to facilitate efficient research practices and broader knowledge dissemination, both within academic circles and industries influenced by energy trends. The design this student team will work to incorporate includes: - Design Architecture and System Design: Develop a comprehensive system architecture, outlining the interaction between the Large Language Model (LLM), the web application, and cloud infrastructure. This student team will work to define component roles, interfaces, and data flows to ensure seamless integration. - Design for fault tolerance and high availability. This student team will work to implement redundancy and failover mechanisms to minimize service disruptions. This student team will also work to structure the architecture with cost efficiency in mind. This student team will work to utilize resource allocation strategies that balance performance requirements with budget considerations. The student team will work to optimize system components for responsiveness and efficiency. This student team will work to employ caching, load balancing, and other performance-enhancing techniques. The results phase this student team will work to accomplish include: - Data Collection and Preprocessing. This student team will work to gather a diverse set of energy-related documents in PDF and other formats. - This student team will work to perform Optical Character Recognition (OCR) to extract text from PDFs and documents. - This student team will work to clean and preprocess the text data, including handling noise, formatting issues, and errors. - Data Labeling and Annotation: This student team will work to manually label and annotate a subset of the data for training and validation. Labels could include categorization (e.g., renewable energy, fossil fuels), key information extraction (e.g., dates, quantities), sentiment analysis, etc. - Model Selection and Training: This student team will work to choose a suitable pre-trained language model architecture (e.g., BERT, GPT-3) as a starting point. This student team will work to fine-tune the selected model using the labeled energy data to make it domain-specific. This student team will work to experiment with hyperparameters, optimization techniques, and training strategies to achieve desired performance. - Web Application Development: This student team will work to develop a user-friendly web interface using a framework like Flask or Django. - This student team will work to implement a mechanism for users to upload energy-related documents and receive analysis results. - This student team will work to integrate the trained LLM into the application to process user input and generate insights. - Model Evaluation and Iteration: This student team will work to evaluate the performance of the trained LLM using validation datasets and metrics relevant to your project's goals (e.g., accuracy, information extraction precision/recall), and to iterate on the model training and fine-tuning based on evaluation results to improve accuracy and relevance. - This student team will work to deploy the web application on a suitable server or cloud platform and ensure the application is accessible to researchers and can handle a reasonable amount of user traffic. - This student team will work to provide comprehensive documentation on how to use the web application and interpret the model's results. - This student team will work to gather feedback from potential users or researchers on the web application's usability and functionality. The student team will also work to refine the web interface based on user feedback to ensure it meets the researchers' needs effectively. Ultimately, this student team is working to create an Energy Large Language Model that will deliver a fully trained Large Language Model (LLM) specialized in energy data analysis. The LLM will excel in semantic search, information retrieval, and summarization and classification tasks. The student team will also work to create a intuitive web application tailored for energy researchers. The application's integration with the LLM will empower researchers to access energy insights efficiently. The team will also provide in-depth user documentation resources to ensure strong tool utilization. This project result will be Open Source: This initiative will foster collaboration among universities, encouraging knowledge sharing, innovations, and advancements within academia.
UW Applied Physics Laboratory
Track Foraging Bats in the Union Bay Natural Area
This student team will work to build ultrasonic microphone arrays to track foraging bats in the Union Bay Natural Area (UBNA) that is immediately adjacent to the UW campus. Bats are an important ecosystem indicator, and their biological sonar system continues to inspire engineers in adaptive sensing designs. Data collected in the UBNA using low-cost single microphone recorders since 2021 has shown stable bat activities in the UBNA in May to early October. In particular, in the call sequences frequent foraging events are observed that simultaneously involve multiple bat individuals or species. By working to deploy microphone arrays in the UBNA, this student team will work to open the door for understanding the rich behavioral repertoire of foraging bats as they interact with their prey and each other through both sounds and movements; it is possible that engineering inspiration for sonar-guided autonomous sensing may be drawn from the results accomplished with this project. Bats in the UBNA emit echolocation calls in the ultrasonic frequency range (25-80 kHz; with three major groups: 25-35 kHz, 30-40 kHz, and 40-80 kHz). In this frequency range sounds are subject to strong absorption. In addition, bat echolocation calls are directional, with the beampattern dynamically modulated depending on the foraging context (e.g., distance to prey, prey type) and the environment. In general, the higher the frequency, the stronger the air absorption, and the more directional the sonar beam. These factors in combination limit the effective spatial span of a microphone array, even though a longer baseline is typically favorable for source localization. The microphone array this student team will work to develop through this project should be able to track bats in all three frequency groups and should be easily deployable by a two-person team in the UBNA field condition. The array should be able to operate autonomously, with configurable on-off cycles, the capability to collect full-bandwidth data for post-analysis, and a minimum length of continuous operation of 12 hours. The outcomes this student team will work to accomplish include: -- Microphone arrays (2-3, depending on material cost), operating software, design diagrams and code documentation -- Recording from lab and field testing -- Implementation of tracking algorithms (optional, but this will be super cool to see!)
UW CoMotion
In the Slot – Umpire Training Tool
The Umpire Perspective Training Tool is a system (hardware and software) that would allow for umpire strike zone evaluations to be done from the umpire’s perspective. Currently, all training is done using baseballs on a stick at slow speeds or outside the field evaluations by trainers. There is no tool available for umpires to learn the strike zone from their personal perspective. While there are numerous studies and publications discussing the batter's perspective, there are are no equivalent analyses for umpires (See Journal of Experimental Psychology: Human Perception and Performance. 1993, Vol. 19, No. 1, 3-14 for an example). This student team will work to create a training system to be used off-line and not an instant ball/strike indicator. The student team will work to create a set of glasses (not AR/VR headset) that fits under the mask that can record pitches using a simulated batter but live pitching. Seasoned umpires agree that a camera mounted on top of the umpire's head does not capture what they see during a pitch. After the session, the recording would be downloaded and run through ML/AI to determine for each pitch: bottom of zone, top of zone, and projected plate volume which the ball travels through. A tally of balls and strikes as well as a graphic showing the umpire’s bias (e.g., low strikes, outside corner etc.) could then be shown and pitches with the plate volume overlay could be reviewed. This visualization would be used as a teaching tool between trainer and student umpire. The student team could also work to collect other data, such as head movement and positioning. The design parameters this student team will work to incorporate include: * High School and above baseball field dimensions for home plate, batter's box, and pitcher's mound * 60 - 90 mph fastball using a standard baseball traveling through the strike one * Data collection device which fits within the standard gear a home plate umpire wears and does not interfere with typical umpire mechanics * Strike definition is can be adjusted according the level of play (e.g., Little League, MLB, etc.) and batter * Software analysis tool can visually display calculated strike zone overlay The outcomes this student team will work to achieve are: 1) Determine the video capture rate and equipment required to collect data during a strike zone training session; 2) Develop a prototype ML/AI system for data analysis that correctly calculates the strike zone for a given batter and can display where the pitch intersected the strike zone volume; 3) A recommended device design criteria and 3D model of a the proposed final device; 4) Recommendations for next steps; and most importantly 5) Have fun and be challenged.
![](https://www.engr.washington.edu/industry/capstone-projects/images/SwiftDraw_UWMed-6670ae4a8a9c1.jpeg)
UW Department of Laboratory Medicine and Pathology
Modeling Patient Throughput Across Diverse Phlebotomy Settings to Decrease Wait Times
Drawing blood from patients for laboratory testing, or phlebotomy, is one of the highest volume procedures performed in health care. Providing these services depends on a number of factors, including physical space, number of workstations, number of draw stations, staff, and efficiency of the processes required to check patients in, identify their laboratory orders, and perform the blood draw safely. There are also challenges with coordinating with clinic schedules: during time periods where clinics have more appointments available there may be a larger number of patients than blood draw capacity. This student team will work with the UW Department of Laboratory Medicine and Pathology to develop robust models to understand patient throughput across the their various blood draw locations and perform simulations that model the impact of changes such as staffing levels, times for specific process steps, and clinic schedules. This student team will work to create a generalizable tool/model that would allow the faculty and leaders who oversee these areas to understand the impact of different operational changes to patient throughput and wait times. This student team will work to assess all of the variables that may impact patient throughput metrics, including physical constraints, workflow steps and their efficiency, and an analysis of how information systems are used in the process. This student team will work to create successful models that accurately predict patient throughput metrics, such as number of patients drawn per unit time or number of minutes per patient, when a change is made to the system. The work product this student team will work to create will be one or more models that can predict with a high level of accuracy (<10% error) phlebotomy metrics that are used by the leadership team to assess the impact of making changes across a variety of blood draw settings, including primary care, specialty care, and hospital locations. Ideally, the work product this student team will work to create will be version controlled and shared with departmental staff who are comfortable with Python and/or R.
UW Electrical and Computer Engineering Quantum Technologies Training and Testbed lab (QT3 Lab)
Embedded Subsystem for Atom Detection in a Quantum Computer Testbed
The quantum technologies training and testbed lab, located in the electrical and computer engineering department, is building a quantum computer testbed based on neutral atoms trapped in optical tweezers. Atoms will be trapped in a pre-defined array of optical tweezers in the focal plane of an in-vacuum microscope objective and then detected on an EMCCD camera via fluorescence imaging. Depending on the quantum state of these atoms, they will either fluoresce or not. This student team will work to determine which atoms are fluorescing in as little time as possible. By developing an embedded system within the ARTIQ open-source FPGA framework, using the Camera Link protocol and dedicated subsystems for image processing, this student team will work to design, implement, and test a subsystem for atom detection for the quantum computer testbed. This student team will also work to design a programmable "mock atom array" to test this imaging subsystem based on off-the-shelf optical components and a microdisplay. The design parameters this student team will work to include are the configurable properties of the Camera Link interface, atomic fluorescence rate, imaging system optical design parameters. Key performance indicators for this subsystem are detection fidelity and detection time. This student team will work to design, build, and test this new subsystem within the context of the ARTIQ open-source FGPA hardware framework. Outcomes this student team will work to achieve include: 1. Demonstration of EMCCD camera control and data acquisition over camera link interface connected to the artiq 2. A subsystem architecture compatible with the ARTIQ framework - the main choice here being how to handle image processing to minimize timing overhead. 3. Design and build the imaging subsystem and micro-display based test fixture. 4. Test, provide a report that details the performance of the system, design factors that limit performance, and tradeoffs.