Recent advances in failure diagnosis techniques based on performance data analysis for grid-connected photovoltaic systems

Livera, Andreas; Theristis, Marios; Makrides, George; Georghiou, George E.

doi:10.1016/j.renene.2018.09.101

Cited by 141 publications

(82 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we focus on another practical case of performance degradation: temporal degradation. The temporal degradation can happen by various reasons [29]. To simulate the temporal degradation, we manually drop the PV power output for a certain duration.…”

Section: Feasibility Study: Temporal Degradationmentioning

confidence: 99%

Forecast uncertainty‐based performance degradation diagnosis of solar PV systems

Lee

2020

IET Renewable Power Generation

View full text Add to dashboard Cite

In this study, the authors are interested in estimating how much a PV system underperforms than expected by exploiting forecast uncertainty. For this, they first study a forecast accuracy-related forecast uncertainty metric using the ensemble method based on the dropout technique, which is widely used in deep learning forecasting models. Given the forecast accuracy-related uncertainty metric, the rationale of the authors' approach is that forecast accuracy is likely to decrease compared to the normal case of similar uncertainty metric values if any performance degradation happens. It is because similar uncertainty metric values are likely to show similar forecast accuracy. Therefore, they generate a standard table by simulating possible performance degradation cases and conduct the performance degradation diagnosis by looking up the standard table based on the uncertainty metric. From the experiments, in the case of persistent degradation, they show that their approach estimates the performance degradation with the estimation error of around 1% while an uncertainty-unaware approach shows the estimation error of up to 5%. In the case of temporal degradation, their approach shows the estimation error of around 3%, while the uncertainty-unaware approach does not show meaningful result.

show abstract

Section: Feasibility Study: Temporal Degradationmentioning

confidence: 99%

Forecast uncertainty‐based performance degradation diagnosis of solar PV systems

Lee

2020

IET Renewable Power Generation

View full text Add to dashboard Cite

show abstract

“…These findings help inform a number of ongoing activities focused on further reducing the LCOE of PV electricity, including inverter reliability simulation analyses, spare parts inventory management, cost model estimates for operations and maintenance (O&M), and development of standards for inverter testing. Further, this work demonstrates the utility of ML for diversifying the types of data -beyond numerical data [27]- [29] to text-based information -considered for reliability and failure analyses.…”

Section: Introductionmentioning

confidence: 99%

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

Gunda

Hackett

Kraus³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

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 failure occurring more frequently in early years. These 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. INDEX TERMS inverters, machine learning, natural language processing, photovoltaics, failures, weibull This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication.

show abstract

“…Scientific literature shows a large number of papers describing and analysing failures in the existing PV plants. Most of the studies are focused on the direct current side of the plant [8,9], specifically in the PV modules.…”

Section: Introductionmentioning

confidence: 99%

Diagnosis of failures in Solar Plants based on Performance monitoring

Talayero¹,

Llombart²,

Melero³

2024

RE&PQJ

View full text Add to dashboard Cite

Photovoltaic (PV) solar energy has become a reference in electrical generation. The plants currently installed, and those planned have a huge capacity and occupy large areas. The increase in size of the plants presents new challenges in operation and maintenance areas, such as the optimization of the number of sensors installed, large data management and the reduction of the timework in maintenance. The aim of this paper is to show a methodology, to diagnose failures, based on the measured data in the plant. The methodology used is supervised regression machine learning and comparison algorithms. This methodology allows the study of the sensors, the inverters, the joint boxes and the power reduction caused by soiling. The result would allow the detection of around 1-5% of production loss in the plant. The algorithms have been tested with real data of PV plants, and have detected common failures such as production drops in strings and losses due to soiling.

show abstract

Recent advances in failure diagnosis techniques based on performance data analysis for grid-connected photovoltaic systems

Cited by 141 publications

References 76 publications

Forecast uncertainty‐based performance degradation diagnosis of solar PV systems

Forecast uncertainty‐based performance degradation diagnosis of solar PV systems

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

Diagnosis of failures in Solar Plants based on Performance monitoring

Contact Info

Product

Resources

About