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

Wang, Yan‐Bo; Chang, Ding-Ge; Qin, Shaorui; Fan, Yu-Hang; Mu, Hai‐Bao; Zhang, Guanjun

doi:10.1109/tim.2019.2926688

Cited by 51 publications

(20 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

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%

Towards Secured Online Monitoring for Digitalized GIS Against Cyber-Attacks Based on IoT and Machine Learning

et al. 2021

View full text Add to dashboard Cite

Recently, the Internet of Things (IoT) has an important role in the growth and development of digitalized electric power stations while offering ambitious opportunities, specifically real-time monitoring and cybersecurity. In this regard, this paper introduces a novel IoT architecture for the online monitoring of the gas-insulated switchgear (GIS) status instead of the traditional observation methods. The proposed IoT architecture is derived from the concept of the cyber-physic system (CPS) in Industry 4.0. However, the cyber-attacks and the classification of the GIS insulation defects represent the main challenges against the implementation of IoT topology for the online monitoring and tracking of the GIS status. For this purpose, advanced machine learning techniques are utilized to detect cyber-attacks to conduct the paradigm and verification. Different test scenarios on various defects in GIS are performed to demonstrate the effectiveness of the proposed IoT architecture. Partial discharge pulse sequence features are extracted for each defect to represent the inputs for IoT architecture. The results confirm that the proposed IoT architecture based on the machine learning technique, that is the extreme gradient boosting (XGBoost), can visualize all defects in the GIS with different alarms, besides showing the cyber-attacks on the networks effectively. Furthermore, the defects of GIS and the fake data due to the cyber-attacks are recognized and presented on the dashboard of the proposed IoT platform with high accuracy and more clarified visualization to enhance the decisionmaking about the GIS status.INDEX TERMS Internet of things; machine learning; cyber-security; gas-insulated switchgear, partial discharge.

show abstract

Section: Introductionmentioning

confidence: 99%

Towards Secured Online Monitoring for Digitalized GIS Against Cyber-Attacks Based on IoT and Machine Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…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%

Applications of the Acoustic Method in Partial Discharge Measurement: A Review

Ilkhechi

Samimi

2021

IEEE Trans. Dielect. Electr. Insul.

111

View full text Add to dashboard Cite

This paper reviews the main features of acoustic emission technique. First, the characteristics of acoustic signals and their physics are addressed. Then, the structure of acoustic sensors employed for capturing signals is studied. In the next step, the acoustic method of PD measurement is compared with the standard electrical method. Afterward, the applications of AET in PD measurement in different equipment are summarized. All acoustic method and combined acoustic-electrical method for PD localization in transformers are discussed. Moreover, the applications of AET in the monitoring of GIS systems are explained, along with the acoustic behaviors of moving particles in these systems. Finally, the general considerations in the signal processing of the acoustic signals are reviewed.

show abstract

“…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%

Wind power prediction based on high-frequency SCADA data along with isolation forest and deep learning neural networks

Lin

Liu

Collu

2020

International Journal of Electrical Power & Energy Systems

115

View full text Add to dashboard Cite

Wind power plays a key role in reducing global carbon emission. The power curve provided by wind turbine manufacturers offers an effective way of presenting the global performance of wind turbines. However, due to the complicated dynamics nature of offshore wind turbines, and the harsh environment in which they are operating, wind power forecasting is challenging, but at the same time vital to enable condition monitoring (CM). Wind turbine power prediction, using supervisory control and data acquisition (SCADA) data, may not lead to the optimum control strategy as sensors may generate non-calibrated data due to degradation. To mitigate the adverse effects of outliers from SCADA data on wind power forecasting, this paper proposed a novel approach to perform power prediction using high-frequency SCADA data, based on isolate forest (IF) and deep learning neural networks. In the predictive model, wind speed, nacelle orientation, yaw error, blade pitch angle, and ambient temperature were considered as input features, while wind power is evaluated as the output feature. The deep learning model has been trained, tested, and validated against SCADA measurements. Compared against the conventional predictive model used for outlier detection, i.e. based on Gaussian processes, the proposed integrated approach, which coupled IF and deep learning, is expected to be a more efficient tool for anomaly detection in wind power prediction.

show abstract

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

Cited by 51 publications

References 29 publications

Towards Secured Online Monitoring for Digitalized GIS Against Cyber-Attacks Based on IoT and Machine Learning

Towards Secured Online Monitoring for Digitalized GIS Against Cyber-Attacks Based on IoT and Machine Learning

Applications of the Acoustic Method in Partial Discharge Measurement: A Review

Wind power prediction based on high-frequency SCADA data along with isolation forest and deep learning neural networks

Contact Info

Product

Resources

About