Fault detection of photovoltaic array based on Grubbs criterion and local outlier factor

Ding, Kun; Zhang, Jingwei; Ding, Hanxiang; Liu, Yongjie; Chen, Fudong; Li, Yuanliang

doi:10.1049/iet-rpg.2019.0957

Cited by 21 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Statistical methods of anomaly detection: These methods are based on statistical data analysis and detect anomalies based on deviations from the norm. Examples include the Grubbs test, the Chauvenet test, and the deviation from normal distribution test [ 25 ]. 2.…”

Section: Related Workmentioning

confidence: 99%

Ultra-Lightweight Fast Anomaly Detectors for Industrial Applications

Kocon,

Malesa,

Rapcewicz

2023

Sensors

View full text Add to dashboard Cite

Quality inspection in the pharmaceutical and food industry is crucial to ensure that products are safe for the customers. Among the properties that are controlled in the production process are chemical composition, the content of the active substances, and visual appearance. Although the latter may not influence the product’s properties, it lowers customers’ confidence in drugs or food and affects brand perception. The visual appearance of the consumer goods is typically inspected during the packaging process using machine vision quality inspection systems. In line with the current trends, the processing of the images is often supported with deep neural networks, which increases the accuracy of detection and classification of faults. Solutions based on AI are best suited to production lines with a limited number of formats or highly repeatable production. In the case where formats differ significantly from each other and are often being changed, a quality inspection system has to enable fast training. In this paper, we present a fast method for image anomaly detection that is used in high-speed production lines. The proposed method meets these requirements: It is easy and fast to train, even on devices with limited computing power. The inference time for each production sample is sufficient for real-time scenarios. Additionally, the ultra-lightweight algorithm can be easily adapted to different products and different market segments. In this work, we present the results of our algorithm on three different real production data gathered from food and pharmaceutical industries.

show abstract

Section: Related Workmentioning

confidence: 99%

Ultra-Lightweight Fast Anomaly Detectors for Industrial Applications

Kocon,

Malesa,

Rapcewicz

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Ding et al [156] For the SPV system to which it is connected, each converter employs its MPPT algorithm. When subjected to uniform solar radiation, the operational voltage and power output of each panel tend to be equal under this topology.…”

Section: Merits and Demerits Of The Spv Systemmentioning

confidence: 99%

A Review on Factors Influencing the Mismatch Losses in Solar Photovoltaic System

Dhass

Beemkumar

Harikrishnan³

et al. 2022

International Journal of Photoenergy

View full text Add to dashboard Cite

In the last two decades, it is persistently emphasized to develop energy generation systems free from greenhouse gas emissions since these gases cause global warming, and it leads to unpredictable monsoons. Consequently, it might not be a conducive environment for human beings and animals to dwell. To ascertain the green environment for the next generations and reduce the use of fossil fuels, renewable energy sources are highly suggested to generate electrical energy. Solar photovoltaic is reckoned to be one of the promising methods to generate electricity; however, it has a lower conversion value due to various losses resulting from external and internal parameters. Among various losses that occurred in the solar photovoltaic system, mismatch loss is imperative, which causes the system to perform poorly. Solar photovoltaic systems have made topical advances in the use of highly effective solar cell materials to achieve high efficiency. In this analysis, performance parameters are influenced by the internal and external conditions of the solar photovoltaic systems and they lead to an increase in the loss of the system. The present review is focused to fetch fruitful information on the several studies that analyzed the effects on the solar photovoltaic systems of parasitic resistances, dust generated by tresses, clouds, solar radiation, temperature, relative humidity, different connection topologies, circuit implementation for partial shading, and remedies suggested by the potential authors.

show abstract

“…A variety of conditions have benefitted from the use of the Grubbs test to detect the presence of outliers [45][46][47][48][49][50][51][52][53][54][55]. The most significant restriction of the Grubbs test is that the thinking quantity of the outliers, denoted by the letter k, must be given…”

Section: ( )mentioning

confidence: 99%

Outlier and Normality Testing of the Residuals from the Carreau-Yasuda Model in Fitting the Rheological Behavior of the Non-Newtonian fluid TF2N

Shukor¹

2021

Bioremed Sci Technol Res

View full text Add to dashboard Cite

Non-Newtonian fluids include a variety of regularly encountered substances such as custard, honey, toothpaste, starch suspensions (including starch from corn starch), paint, blood, melted butter, and hairspray. For decades, scientists have investigated non-Newtonian fluid behavior and produced models to aid in the characterization of non-Newtonian fluid behavior. In addition to data interpolation and extrapolation, the outputs of these models may be utilized for material classification based on model parameters and aid with the simulation of computational fluid dynamics. The Carreau-Yasuda model fitted to the rheological behavior of the non-Newtonian fluid1-butyl-3-methylimidazolium bis(trifluoromethylsulfonyl) imide ([emim][TF2N]) was checked for its conformation to the normal distribution of its residual using the normality tests , which was found not to pass all of the test. After checking for the presence of an outlier using the Grubbs â€˜test, no outlier was detected. The ROUT method was then applied to detect the presence of outliers and three outliers were found and removed. The normality checks performed on the cleaned residues gave acceptable results in terms of normality tests and visual conformation of the residual, Q-Q plot and overlaid normality curve to the histogram, indicating that the model is now appropriate for the data.

show abstract

Fault detection of photovoltaic array based on Grubbs criterion and local outlier factor

Cited by 21 publications

References 36 publications

Ultra-Lightweight Fast Anomaly Detectors for Industrial Applications

Ultra-Lightweight Fast Anomaly Detectors for Industrial Applications

A Review on Factors Influencing the Mismatch Losses in Solar Photovoltaic System

Outlier and Normality Testing of the Residuals from the Carreau-Yasuda Model in Fitting the Rheological Behavior of the Non-Newtonian fluid TF2N

Contact Info

Product

Resources

About