A5028978263- Fault Detection and Control Systems
- Risk and Safety Analysis
- Graphite, nuclear technology, radiation studies
- Advanced Battery Technologies Research
- Nuclear Engineering Thermal-Hydraulics
- Process Optimization and Integration
- Engineering Diagnostics and Reliability
- Advancements in Battery Materials
- Water Quality Monitoring and Analysis
- Nuclear Physics and Applications
- Radiation Detection and Scintillator Technologies
- Gear and Bearing Dynamics Analysis
- Advanced Data Processing Techniques
- Software Reliability and Analysis Research
- Explainable Artificial Intelligence (XAI)
- Advanced Battery Materials and Technologies
- Machine Fault Diagnosis Techniques
- Power Transformer Diagnostics and Insulation
- Low-power high-performance VLSI design
- Petroleum Processing and Analysis
- Material Properties and Failure Mechanisms
- Teaching and Learning Programming
- Big Data Technologies and Applications
- Efficiency Analysis Using DEA
- Digital Storytelling and Education
Idaho National Laboratory
2020-2024
Oak Ridge National Laboratory
2023
Blue Wave Semiconductors (United States)
2023
University of Tennessee at Knoxville
2019-2020
Wind energy is growing increasingly popular in the United States, so it imperative to make as cost competitive possible. Operations and Maintenance (O&M) up 20-25% of total onshore wind projects. Unplanned maintenance contributes approximately 75% costs (WWEA, 2012). Condition-based strategies intend maximize uptime by reducing amounts unplanned maintenance. This should result an overall decrease turbines produce interesting challenge, because their main shaft rotation both slow...
A tremendous commitment of resources is needed to acquire, understand and apply battery data in terms performance aging behavior. There are many state (SOP) health (SOH) metrics that useful guide alignment batteries end-use, yet how these measured or extracted can make the difference between usable, valuable datasets versus lacks necessary integrity meet baseline confidence levels for SOP/SOH quantification. This work will speak 1) types support SOP SOH evaluations on mechanistic terms, 2)...
Nuclear plant sites collect and store large volumes of data gathered from various equipment systems. These datasets typically include process parameters, maintenance records, technical logs, online monitoring data, failure data. The collection such affords an opportunity to leverage data-driven machine learning (ML) artificial intelligence (AI) technologies provide diagnostic prognostic capabilities within the nuclear power industry, thus reducing operations (O&M) costs. In this way,...
<ns3:p>As part of an initiative to steward research, development, and innovation into the nuclear fuel cycle, Idaho National Laboratory is building Beartooth test bed. will include a cascade centrifugal contactors, glove box lines, solidification dissolution equipment aid in progression novel separation techniques provide hands-on opportunities early-career engineers. incorporate monitoring using sensors machine learning algorithms inform process operators conditions. This research examining...
As integral components of any power plant, transformers sup-ply the generated electricity to grid. However, trans-former’s cellulose-based paper insulation and mineral oilin which it is immersed break down over time under stan-dard operating conditions—or more rapidly due potentialfaults within system. This technical brief exhibits a col-lection diagnostic prognostic techniques that utilitiescan adopted in lieu labor-intense periodic preventive main-tenance routines. Furthermore, models have...
Despite significant attention to online health monitoring and prognostics of bearings, many common indicators are not sensitive early stages degradation. This research investigates the use approximate entropy (ApEn), previously developed for fault diagnostics, as a indicator prognostics. ApEn quantifies regularity signal; bearings degrade, frequency content vibration signals changes affects becomes more chaotic. Early results suggest supports earlier degradation detection predictable...
Nuclear power plants collect and store large volumes of heterogeneous data from various components systems. With recent advances in machine learning (ML) techniques, these can be leveraged to develop diagnostic short-term forecasting models better predict future equipment condition. Maintenance operations then planned advance whenever degraded performance is predicted, thus resulting fewer unplanned outages the optimization maintenance activities. This enables lower costs improves overall...