Industry-Sponsored Student Capstone Projects

This project developed a tool to visualize drone flight using both simulated and real telemetry data. The system creates a complete pipeline that takes raw flight data, converts it into a standardized format, and generates a realistic 3D animation of the drone’s motion. The key components included a 6DOF physics-based simulation, telemetry data processing, and an interactive user interface that was built in MATLAB/Simulink. This framework allows users to analyze drone behavior and compare simulated results with real-world data, supporting the development of promotional material to highlight product capabilities.

This project focused on the development of a navigation filter for an airframe deployed from a carrier drone, addressing the need for reliable autonomous operation after separation. The system was designed to estimate the airframe’s position, velocity, and orientation using onboard sensors such as magnetometers, gyroscopes, and accelerometers, with optional GPS input and the ability to continue operating when GPS measurements were unreliable or unavailable. The design also included transfer alignment from the drone’s navigation system so the airframe could receive initial state data before deployment. The student team used modeling, simulation, bench testing, and system-level testing to evaluate sensor fusion, filter stability, tunability, and performance under varying flight conditions, with supporting documentation and software intended to make the navigation capability usable and configurable.

ClairVoyan is a vision-based Detect-and-Avoid (DAA) framework for small unmanned aerial vehicles (UAVs), developed in partnership with Guide Air Labs. Unlike conventional DAA systems relying on radar or ADS-B transponders, which are too heavy for small platforms, ClairVoyan employs a passive, camera-only pipeline integrating deep learning detection to identify non-cooperative airborne intruders at long range. The system targets compliance with RTCA DO-387 operational performance standards.

Project SHIELD (Smart Hardware Inspection for Early Latency Detection) addresses a critical gap in safety-critical embedded systems: the lack of proactive, on-device sensor failure detection. Sensor degradation in UAVs, autonomous vehicles, and medical devices often goes undetected until functional loss, with potentially catastrophic consequences. To support a predictive TinyML framework, the team designed a custom DAQ PCB around an ESP32-S3, integrating eight sensor modalities including IMU, barometer, microphone, temperature, photodiode, vibration, and current sensors. Data collection spans nominal operation and fault injection, generating a labeled dataset for ML model training.

Harper Engineering Company sought a fresh look at its 35,000-square-foot Renton factory to better understand how parts and materials moved through the facility and where layout or process changes could improve operations. The project sought to develop a digital factory floor map and document current flow from raw materials and purchased components through machining, fabrication, sub-assembly, final assembly, and shipping. The student team examined inventory kitting, work instructions, and how parts and subassemblies were presented to operators, with the goal of identifying opportunities to improve clarity, ergonomics, material handling, and overall efficiency. The team provided Harper with a current-state view of its operation along with a conceptual “golden cell” design and related recommendations for future improvement.

Productivity often declines in “Third Place” settings like commuting or between meetings, where attention is fragmented and context switching is frequent. Mobile professionals, especially executives, may lose ideas, disrupt cognitive flow, and delay follow-ups. Existing tools are fragmented and non-agentic, forcing users to manually connect capture, organization, and action across apps. This project proposes an agentic AI workflow that integrates a lightweight assistant with digital inking and immersive communication, enabling fast capture, structured next steps, and seamless follow-up without leaving the current context.

Hytek Finishes currently uses manual beacons to communicate machine statuses; but these systems only provide basic visual signals and are found ineffective by workers. The existing system also fails to notify all relevant personnel of status changes. This project developed an integrated system featuring four-state industrial beacons and a touchscreen interface that combines visual indication, issue logging, and notifications while withstanding the plant’s harsh environments. Through its scalable design and integration with company servers, the system enables comprehensive issue tracking, enhancing communication, minimizing downtime, and supporting process optimization at Hytek Finishes.

Test engineers rely on complex computer networks to coordinate tests on products. When a fault occurs in the network, engineers need to be notified so that tests can resume as soon as possible. This project solves the problem of test networks going down for extended periods of time by notifying engineers as soon as an issue is detected. The system continuously monitors and logs the status of the network. Once a fault is detected, engineers are notified via email to check the logs to determine which part of the network has failed, preventing major delays.

This project addressed limitations in a mechanical polishing system that relied on manual, skill-dependent angular adjustments. It aimed to convert that process into a hands-free polishing platform by integrating motorized goniometer stages for tilt and theta adjustment, a motorized z-stage, and a Windows-based graphical interface. The system was intended to support very fine angular changes on the order of less than 0.01 degrees, provide variable sample loading from 20 g to 400 g, and guide operation through an intuitive interface that reduced the need for manual expertise. These results will provide a more reliable and accessible method for angular adjustment, along with a gentle, repeatable touchdown sequence designed to reduce the risk of sample damage during polishing.

The project developed a technoeconomic and experimental evaluation framework for a 100 t/yr nanoparticle manufacturing process. The analysis estimated capital costs, annual operating costs, CO2e emissions, and material cost per kilogram while identifying major cost drivers in the baseline process. Alternative routes, such as reagent substitution or process modification, were evaluated for potential economic advantages and used to guide experimental nanoparticle synthesis. The resulting materials were intended for fabrication and testing in coin or pouch cells at the Washington Clean Energy Testbeds, providing proof-of-concept prototypes and supporting comparison of baseline and alternative manufacturing approaches.

This project focused on a Phase 1 effort to support the search for resin formulations that could improve compression performance in carbon fiber reinforced polymer composites for weight-sensitive structures such as aircraft wings. The project focused on aerogel-and-epoxy systems as a possible route to co-continuous crosslinks associated with resin stiffness and toughness. The student team surveyed commercial aerogel products, compositions, manufacturers, and factors affecting nanoparticle crosslink formation, including surface chemistry, particle size, loading, and host material. The project also aimed to document crosslinks in a selected aerogel using microscopy and SEM, and to create a data-compilation method that could combine supplier datasheets and generated test data into a single structured table while identifying duplicate or equivalent property labels.

The project focused on designing and prototyping a compact, solar-powered oceanographic buoy intended to operate an underwater camera and data transfer system for up to a year with minimal batteries. The buoy concept needed to integrate solar panels, onboard batteries, charge control electronics, a control computer, a camera, and a cellular antenna, along with a mounting frame designed with buoyancy foam, anchoring, and deployment and recovery pick points. The design also needed to target practical field use by keeping the buoy under 1 meter in diameter and about 100 pounds so it could be transported and deployed from a small vessel, while accounting for wave exposure, corrosion, and biofouling. Completion of the prototype enabled MarineSitu to evaluate it for long-term deployment and potential commercialization. This capability would enable persistent underwater ecosystem and biodiversity monitoring at marine conservation sites without cabling the buoy to shore for power.

This project focused on the need to assess whether small, distributed data centers could support lower-carbon heating in Seattle’s dense urban core, where district steam and natural gas systems contribute significantly to building emissions. The student team explored micro-data centers as part of a block-level eco-district strategy, using recovered computing heat as a potential neighborhood energy source while supporting growing data center demand. The project focused on a candidate downtown block or building and examined heating and cooling loads, electrical demand and service capacity, and available space to assess feasibility. The resulting concept includes a block load model, preliminary sizing for the data center and core energy infrastructure, a plan for connecting recovered heat to nearby buildings, and an evaluation of potential energy and carbon benefits, with a conceptual economic review where feasible.

One of Membrion's target markets is semiconductor & electrodeposition wastewaters. In-line metal concentration measurements of these streams are not straightforward due to fluctuations in the quality of customer waters. Conductivity and refractive index can be relatively straightforward measurements to determine metal concentrations, but are convoluted by changes in pH and turbidity. To address this limitation, the project investigated representative wastewater compositions relevant to Membrion’s target market and developed an experimental matrix of mixed-metal solutions containing copper salts, additional metallic salts, and acids. The solutions were characterized using conductivity, pH, turbidity, and refractive index measurements, and the resulting data supported development of a predictive model to estimate copper concentration from these more easily measured parameters. This work aimed to provide a calculator or software tool that could infer copper concentrations in complex process streams where direct measurement was difficult.

Micron sought to better understand how generative AI could accelerate analysis of complex semiconductor manufacturing data and help reveal patterns tied to key fab performance metrics. This project investigated the use of generative AI to explore a large manufacturing dataset from one of Micron’s fabs, with the goal of identifying underlying trends, documenting an effective approach for AI-assisted data discovery, and developing possible process improvement recommendations based on the insights found. This work aimed to clarify how this technology could support faster understanding of difficult manufacturing data and inform future engineering decision-making.