Solar Array Fault Detection using Neural Networks

Rao, Sunil; Spanias, Andreas; Tepedelenlioğlu, Cihan

doi:10.1109/icphys.2019.8780208

Cited by 54 publications

(26 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While neural networks (NNs) have been used in the past for fault detection and classification tasks [4], [16], the set of hyper-parameters to be chosen and the type of architecture is a challenge. Our vision for research monitoring and optimizing a large-scale PV array is summarized in Figure 2.…”

Section: Introductionmentioning

confidence: 99%

Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays

Rao¹,

Muniraju

Tepedelenlioğlu

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Automatic detection of solar array faults reduces maintenance costs and increases efficiency.In this paper, we address the problem of fault detection, localization, and classification in utility-scale photovoltaic (PV) arrays using machine learning methods. More specifically, we develop a series of customized neural networks for detection and classification of solar array faults. We evaluate fault detection and classification using metrics such as accuracy, confusion matrices, and the Risk Priority Number (RPN). We examine and assess the use of customized neural networks with dropout regularizers. We develop and evaluate neural network pruning strategies and illustrate the trade-off between fault classification model accuracy and algorithm complexity. Our approach promises to elevate the performance and robustness of PV arrays and compares favorably against existing methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays

Rao¹,

Muniraju

Tepedelenlioğlu

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…The algorithms can also "learn" the non-linearities of the data which is specifically useful for solar array analytics due to the non-linear PV characteristics. In the case of solar panel fault detection, algorithms such as neural networks can classify a variety of dependent faults with high accuracy [5]. On the other hand, machine learning algorithms [8] can provide an endto-end system with reduced number of switching between the panels, as in the case of the connection topology reconfiguration of solar panels.…”

Section: Description Of the Solar Monitoring And Control Systemmentioning

confidence: 99%

“…We have used the k-means algorithm as part of our Cyber Physical systems project [6] and have described a method to detect and characterize solar array faults [4,5,17]. In this education project, we form a J-DSP simulation of k-means for fault detection to present to class for the purpose of showing how ML is used in solar energy systems.…”

Section: Module and Exercise On Fault Detection Using Machine Learningmentioning

confidence: 99%

“…While the k-means clustering algorithm can be used for fault detection, they fail when the variance in the dataset is high [5]. Also, several commonly occurring faults and shading conditions are not identified by k-means algorithm.…”

Section: Module and Exercise On Fault Detection Using Machine Learningmentioning

confidence: 99%

“…Although there are distinct courses in solar energy generation and machine learning, the creation of content at the overlap of these two areas offers several opportunities for education and research. Machine learning [1] promises to solve several problems in solar energy generation including a) fault detection [2,3,4,5], b) shading prediction [6], and c) topology optimization [7,8,9]. Preparing students early in their plans of study to tackle these problems requires: a) training in machine learning, b) exposition to solar energy systems simulation [10], c) skill building in terms of developing or using software to integrate machine learning to obtain solar system analytics and control the overall system [11].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Board 162: Online Modules to Introduce Students to Solar Array Control using Neural Nets

Narayanaswamy

Shanthamallu²,

Dixit

et al.

2019 ASEE Annual Conference &Amp; Exposition Proceedings

Self Cite

View full text Add to dashboard Cite

He is currently a graduate student in the school of electrical, computer and energy engineering at ASU, Tempe, AZ. He completed an internship with Qualcomm R&D this summer. His current research interests include developing automated techniques for topology reconfiguration in PV panels to maximize power and to investigate other possible metrics and deep learning frameworks that can be used for speaker diarization. Mr. Uday Shankar Shanthamallu "I received my B.S degree in Electronics and Communications from the National Institute of Engineering, India in 2011. I am currently pursuing my Master's and PhD program in Electrical Engineering at Arizona State University(ASU). I am advised by Dr. Andreas Spanias. I joined Sensor, Signal and Information Processing Center (SenSIP) at ASU in Jan 2016. My research interests lie at the overlap of sensors and Machine learning and Big Data including, but not limited to Pattern recognition and Anomaly detection. In summer 2016, I did a summer internship at NXP Semiconductors where I worked on sensor data analytics for anomaly detection. I worked on integrating machine learning algorithms on an embedded sensor systems for Internet of Things applications, which can identify anomalies in real time. Before joining ASU, I worked as Systems engineer for 4 years at

show abstract

Generative Adversarial Network for Synthetic Imaging Data of Sub-optimal Conditions in Photovoltaic Panels

Jiménez-Delgado

Méndez-Porras

Alfaro-Velásco

2022

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Solar Array Fault Detection using Neural Networks

Cited by 54 publications

References 27 publications

Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays

Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays

Board 162: Online Modules to Introduce Students to Solar Array Control using Neural Nets

Generative Adversarial Network for Synthetic Imaging Data of Sub-optimal Conditions in Photovoltaic Panels

Contact Info

Product

Resources

About