2020
DOI: 10.1109/tim.2019.2926688
|View full text |Cite
|
Sign up to set email alerts
|

Separating Multi-Source Partial Discharge Signals Using Linear Prediction Analysis and Isolation Forest Algorithm

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
20
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 51 publications
(20 citation statements)
references
References 29 publications
0
20
0
Order By: Relevance
“…PD examination has been achieved by machine learning-based approaches, e.g. support vector machine [20], random forests [21], artificial neural network [22], decision trees (DT) [23], and genetic algorithm [24]. Different partial detection methods have been investigated for condition monitoring [25].…”
Section: Introductionmentioning
confidence: 99%
“…PD examination has been achieved by machine learning-based approaches, e.g. support vector machine [20], random forests [21], artificial neural network [22], decision trees (DT) [23], and genetic algorithm [24]. Different partial detection methods have been investigated for condition monitoring [25].…”
Section: Introductionmentioning
confidence: 99%
“…In such a circumstance, it is appropriate to employ a separation method to detect each PD individually. A new multi-source PD separation method is presented in [2]. Isolation forest algorithm and linear prediction analysis are used to separate different PD signals by calculating a two-dimensional feature space.…”
Section: General Considerationmentioning
confidence: 99%
“…THE insulation system of high voltage apparatuses is one of the most important factors affecting their reliability [1]. Therefore, it is necessary to monitor the insulation condition during operation [2][3][4]. Partial discharge (PD) measurement is one of the sensitive ways to discover the insulation condition [5].…”
Section: Introductionmentioning
confidence: 99%
“…3a), triggered by the harsh offshore environment. On the other hand, IF can be considered as an effective method when Gaussian distributions cannot be assumed [18]. Furthermore, to capture the stochastic nature of the wind, the current study is using a very high-frequency SCADA database, with a sampling rate of 1 second, which created large-sized datasets with high dimensional input features, including wind speed, nacelle orientation, yaw error, blade pitch angle, and ambient temperature.…”
Section: Accuracy Of Forecastingmentioning
confidence: 99%