A Machine Learning Evaluation of Maintenance Records for Common Failure Modes in PV Inverters

Gunda, Thushara; Hackett, Sean; Kraus, Laura; Downs, Christopher; Jones, Ryan; McNalley, Christopher; Bolen, Michael; Walker, Andy

doi:10.1109/ACCESS.2020.3039182

Title: A Machine Learning Evaluation of Maintenance Records for Common Failure Modes in PV Inverters

Full Record
Other Related Research

Abstract

Inverters are a leading source of hardware failures and contribute to significant energy losses at photovoltaic (PV) sites. An understanding of failure modes within inverters requires evaluation of a dataset that captures insights from multiple characterization techniques (including field diagnostics, production data analysis, and current-voltage curves). One readily available dataset that can be leveraged to support such an evaluation are maintenance records, which are used to log all site-related technician activities, but vary in structuring of information. Using machine learning, this analysis evaluated a database of 55,000 maintenance records across 800+ sites to identify inverter-related records and consistently categorize them to gain insight into common failure modes within this critical asset. Communications, ground faults, heat management systems, and insulated gate bipolar transistors emerge as the most frequently discussed inverter subsystems. Further evaluation of these failure modes identified distinct variations in failure frequencies over time and across inverter types, with communication failures occurring more frequently in early years. Increased understanding of these failure patterns can inform ongoing PV system reliability activities, including simulation analyses, spare parts inventory management, cost estimates for operations and maintenance, and development of standards for inverter testing. Advanced implementations of machine learning techniques coupled with standardization ofmore »« less

Authors:

;

; Kraus, Laura; Downs, Christopher; Jones, Ryan; McNalley, Christopher; Bolen, Michael;

Publication Date:: Wed Jan 01 00:00:00 EST 2020

Research Org.:: Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); National Renewable Energy Lab. (NREL), Golden, CO (United States)

Sponsoring Org.:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office; USDOE National Nuclear Security Administration (NNSA)

OSTI Identifier:: 1811161

Alternate Identifier(s):: OSTI ID: 1738917; OSTI ID: 1755746; OSTI ID: 1861218

Report Number(s):: SAND-2020-13529J; NREL/JA-5C00-78736
Journal ID: ISSN 2169-3536; 9272625

Grant/Contract Number:: 34172; AC04-94AL85000; NA-000352; AC36-08GO28308

Resource Type:: Published Article

Journal Name:: IEEE Access

Additional Journal Information:: Journal Name: IEEE Access Journal Volume: 8; Journal ID: ISSN 2169-3536

Publisher:: Institute of Electrical and Electronics Engineers

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING; 14 SOLAR ENERGY; inverters; machine learning; natural language processing; photovoltaics; failures; weibull

Citation Formats


                    Gunda, Thushara, Hackett, Sean, Kraus, Laura, Downs, Christopher, Jones, Ryan, McNalley, Christopher, Bolen, Michael, and Walker, Andy. A Machine Learning Evaluation of Maintenance Records for Common Failure Modes in PV Inverters.  United States: N. p., 2020. 
Web.  doi:10.1109/ACCESS.2020.3039182.

Copy to clipboard


                    Gunda, Thushara, Hackett, Sean, Kraus, Laura, Downs, Christopher, Jones, Ryan, McNalley, Christopher, Bolen, Michael, & Walker, Andy. A Machine Learning Evaluation of Maintenance Records for Common Failure Modes in PV Inverters.  United States.  https://doi.org/10.1109/ACCESS.2020.3039182

Copy to clipboard


                    Gunda, Thushara, Hackett, Sean, Kraus, Laura, Downs, Christopher, Jones, Ryan, McNalley, Christopher, Bolen, Michael, and Walker, Andy. Wed .  
"A Machine Learning Evaluation of Maintenance Records for Common Failure Modes in PV Inverters".  United States.  https://doi.org/10.1109/ACCESS.2020.3039182.

Copy to clipboard


                    
@article{osti_1811161,

  title        = {A Machine Learning Evaluation of Maintenance Records for Common Failure Modes in PV Inverters},

  author       = {Gunda, Thushara and Hackett, Sean and Kraus, Laura and Downs, Christopher and Jones, Ryan and McNalley, Christopher and Bolen, Michael and Walker, Andy},

  abstractNote = {Inverters are a leading source of hardware failures and contribute to significant energy losses at photovoltaic (PV) sites. An understanding of failure modes within inverters requires evaluation of a dataset that captures insights from multiple characterization techniques (including field diagnostics, production data analysis, and current-voltage curves). One readily available dataset that can be leveraged to support such an evaluation are maintenance records, which are used to log all site-related technician activities, but vary in structuring of information. Using machine learning, this analysis evaluated a database of 55,000 maintenance records across 800+ sites to identify inverter-related records and consistently categorize them to gain insight into common failure modes within this critical asset. Communications, ground faults, heat management systems, and insulated gate bipolar transistors emerge as the most frequently discussed inverter subsystems. Further evaluation of these failure modes identified distinct variations in failure frequencies over time and across inverter types, with communication failures occurring more frequently in early years. Increased understanding of these failure patterns can inform ongoing PV system reliability activities, including simulation analyses, spare parts inventory management, cost estimates for operations and maintenance, and development of standards for inverter testing. Advanced implementations of machine learning techniques coupled with standardization of asset labels and descriptions can extend these insights into actionable information that can support development of algorithms for condition-based maintenance, which could further reduce failures and associated energy losses at PV sites.},

  doi          = {10.1109/ACCESS.2020.3039182},

  journal      = {IEEE Access},

  number       = ,

  volume       = 8,

  place        = {United States},

  year         = {Wed Jan 01 00:00:00 EST 2020},

  month        = {Wed Jan 01 00:00:00 EST 2020}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Publisher's Version of Record
https://doi.org/10.1109/ACCESS.2020.3039182

Other availability

Search WorldCat to find libraries that may hold this journal

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

Austin Sustainable and Holistic Integration of Energy Storage and Solar PV [Austin SHINES]. Final Report, Version 2

Technical Report Popp, Anna ; Hughes, Jennifer

The Austin SHINES project and solution is a software management platform, for an electric grid with a high penetration of dispersed photovoltaic (PV) solar generation sites, which maintains the traditional power quality and reliability associated with grid service. This project developed and deployed the platform as a Distributed Energy Resource Management System (DERMS), engaging multiple advanced controls, to evaluate operation and optimization of a fleet of diverse DER assets, installed at several locations among Austin Energy’s customers and distribution system. The project also produced a methodology to create a replicable DERMS template, adaptable to other regions and market structures. Last, Austin SHINES aimed to demonstrate the solution’s methodology would enable the DER grid ecosystem to serve load at a technical cost (System Levelized Cost of Electricity, or System LCOE) of less than the U.S. Department of Energy SHINES program metric ofmore »« less
https://doi.org/10.2172/1661670

Full Text Available
The SURE House (Solar Decathlon 2015)

Technical Report Nastasi, John ; May, Edwin

Coastal towns and cities across the Northeastern US, with their high population density, aged utility infrastructure, and unique geography, are increasingly vulnerable to climate change related storm events. In October 2012 superstorm Sandy highlighted the fragility of our current coastal building types and made clear the need for a new model of design and construction which works to understand and mitigate these weaknesses. Dramatic changes in public policy, championed by both The Federal Emergency Management Agency (FEMA) and the National Flood Insurance Program (NFIP) are driving the rebuilding of these shore communities, often resulting in costly renovations, un-sustainable neighborhood configurationsmore »« less
https://doi.org/10.2172/1378086

Full Text Available
Generation of Data-Driven Expected Energy Models for Photovoltaic Systems

Journal Article Hopwood, Michael W. ; Gunda, Thushara - Applied Sciences

Although unique expected energy models can be generated for a given photovoltaic (PV) site, a standardized model is also needed to facilitate performance comparisons across fleets. Current standardized expected energy models for PV work well with sparse data, but they have demonstrated significant over-estimations, which impacts accurate diagnoses of field operations and maintenance issues. This research addresses this issue by using machine learning to develop a data-driven expected energy model that can more accurately generate inferences for energy production of PV systems. Irradiance and system capacity information was used from 172 sites across the United States to train a series of models using Lasso linear regression. The trained models generally perform better than the commonly used expected energy model from international standard (IEC 61724-1), with the two highest performing models ranging in model complexity from a third-order polynomial with 10 parameters (more »« less
https://doi.org/10.3390/app12041872
Integrated Risk-Informed Condition Based Maintenance Capability and Automated Platform: Technical Report 3

S&T Accomplishment Report Agarwal, Vivek ; Gribok, Andrei V ; Araseethota Manjunatha, Koushik ; ...

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. Thismore »« less
Full Text Available
Policy, Permit, Perform: Using City Benchmarking Data and Building Construction Permit History to Identify Energy Performance Improvements

Technical Report Stevens, Casey ; Tyler, Matt ; Lee, Allen ; ...

The City of Portland (City) and Multnomah County 2015 Climate Action Plan targets a 40 percent reduction in carbon emissions below 1990 levels by 2030. To reach this goal, the plan includes a key objective to reduce the total energy use of existing buildings by 25 percent. Buildings are responsible for one-half of carbon emissions in Portland, Oregon, U.S., and improving their performance is critical to achieving the City’s climate goals. As part of its climate action planning, the City passed an ordinance on April 22, 2015, requiring commercial buildings 20,000 ft2 and larger to benchmark and disclose annual energymore »« less
https://doi.org/10.2172/1477793

Full Text Available

Similar Records