Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Integrated Risk-Informed Condition Based Maintenance Capability and Automated Platform: Technical Report 3

S&T Accomplishment Report ·
OSTI ID:1900393
 [1];  [1];  [1];  [1];  [1];  [1];  [2];  [2];  [2];  [3]
  1. Idaho National Laboratory
  2. PKMJ Technical Services
  3. Public Service Enterprise Group (PSEG) Nuclear, LLC
+ Show Author Affiliations
This project is a collaborative research effort between PKMJ Technical Services LLC, Idaho National Laboratory, and Public Service Enterprise Group (PSEG) Nuclear, LLC. The collaboration, led by PKMJ Technical Services LLC, is part of the industry Funding Opportunity Announcement (FOA) award under Advanced Nuclear Technology Development FOA #DE-FOA-0001817. The pilot demonstration focuses on the Circulating Water System (CWS), an important non-safety-related system that impacts the power generation capability of the plant site. Achieving riskinformed condition-based Predictive Maintenance (PdM) on the CWS will result in significant economic benefits, and the developed methodologies can also be applied to other plant systems. This approach supports an industry goal of ensuring that nuclear power generation remains a viable, economically competitive option in the energy market. Operation and Maintenance (O&M) costs include labor-intensive Preventive Maintenance (PM) programs that involve manually performed inspection, calibration, testing, and maintenance of plant assets at periodic frequencies as well as time-based replacement of assets, irrespective of condition. This project offers an alternative by focusing on riskinformed condition-based maintenance to reduce O&M costs while still maintaining plant health and safety. This report summarizes the progress made toward achieving a risk-informed condition-based maintenance approach. The research and development (R&D) activities presented in this report are associated with development of a nuclear digital platform application, integration of fault signature models, and automated work management processes. The fault signatures and Machine Learning (ML) models are key components in predictive analytics and are heavily leveraged to improve the insights received by existing plant process data sources. Availability of the analysis results within a centralized digital platform enhances efficiency by enabling automation of activities otherwise performed manually. Personnel are presented with enhanced information that can be used to evaluate plant status and risks. Utilizing the enhancements to data analytics supports automated responses, (i.e. issuance of work orders) to address developing equipment faults and thus preventing forced, unplanned shutdowns of components or systems. The R&D activities described within this report lay the foundation for developing and demonstrating a digital automated platform to centralize the implementation of condition monitoring and response to equipment faults. The digital automated platform is cloud-based and designed to enable improved efficiency of plant processes. The digital platform includes content related to maintenance optimization, fault signature analysis, and plant records, which can all be used to support efficiencies when located within a centralized digital platform. These efficiencies could be further enhanced when deployed through industry-wide deployment of the technology to improve insights and processes based upon economies of scale.
Research Organization:
Idaho National Laboratory (INL), Idaho Falls, ID (United States)
Sponsoring Organization:
USDOE Office of Nuclear Energy (NE)
DOE Contract Number:
AC07-05ID14517
OSTI ID:
1900393
Report Number(s):
INL/EXT-21-63561-Rev000
Country of Publication:
United States
Language:
English

Similar Records

Related Subjects

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY
Circulating Water System
Diagnosis and Prognosis Models
Digital Automation Platform
Economic Model
Machine Learning
Markov chain model