A Synchronized Lissajous-Based Method to Detect and Classify Events in Synchro-Waveform Measurements in Power Distribution Networks

Izadi, Milad; Mohsenian‐Rad, Hamed

doi:10.1109/tsg.2022.3148757

Cited by 21 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another research trend in this field is to apply artificial intelligence technology to the analysis disturbance data. For example, [49] used multi-point synchronous waveform data to construct disturbance data into a Lissajous curve from the perspective of image processing and used a convolution neural network to identify and classify the disturbance. Ref.…”

Section: Power Quality Perception and Location Based On Power Disturb...mentioning

confidence: 99%

Power disturbance waveform analysis and proactive application in power systems

Xiao

Zhou

Zhang

et al. 2023

Energy Conversion and Econom

View full text Add to dashboard Cite

Power disturbances, defined as the waveform distortion of a power system under normal or abnormal conditions, contain considerable system and equipment state information. Obtaining equipment and system state information from power disturbance is very important to ensure the safety of power grids. To adapt to the development of power electronics, informatisation and digitisation of power systems, several applications with waveform‐recording devices have obtained large amounts of disturbance waveform data, laying an important foundation for the analysis and application of power disturbance waveform data. First, typical disturbance waveform monitoring devices and a disturbance trigger detection algorithm are introduced. Then, disturbances are classified as switching, fault, or abnormal operations, according to the cause. The characteristics of various typical disturbance waveform data were analysed by combining the simulation and measured data. This paper summarises the application analysis of power disturbance waveform data at both the system and equipment levels. Finally, the construction scheme of a power disturbance waveform data monitoring and analysis platform for two different application scenarios was proposed for commutation failure monitoring and medium‐voltage distribution network fault warning. The research conducted here is expected to support the construction of a power disturbance waveform analysis platform.

show abstract

Section: Power Quality Perception and Location Based On Power Disturb...mentioning

confidence: 99%

Power disturbance waveform analysis and proactive application in power systems

Xiao

Zhou

Zhang

et al. 2023

Energy Conversion and Econom

View full text Add to dashboard Cite

show abstract

“…A CNN and Artificial Neural Network (ANN) were used by the authors of [ 4 ] to classify outage events collected in an operational power distribution system. A CNN was used to classify Power Quality (PQ) events in synchro-waveform measurements made in a power distribution system in [ 5 ], while a Long Short-Term Memory (LSTM) classifier was used in [ 6 ] and a Graph CNN (G-CNN) in [ 7 ]. However, these works require a sufficiently large set of labeled training data.…”

Section: Introductionmentioning

confidence: 99%

Learning from Power Signals: An Automated Approach to Electrical Disturbance Identification within a Power Transmission System

Boyd,

Tyler,

Murphy

et al. 2024

Sensors

View full text Add to dashboard Cite

As power quality becomes a higher priority in the electric utility industry, the amount of disturbance event data continues to grow. Utilities do not have the required personnel to analyze each event by hand. This work presents an automated approach for analyzing power quality events recorded by digital fault recorders and power quality monitors operating within a power transmission system. The automated approach leverages rule-based analytics to examine the time and frequency domain characteristics of the voltage and current signals. Customizable thresholds are set to categorize each disturbance event. The events analyzed within this work include various faults, motor starting, and incipient instrument transformer failure. Analytics for fourteen different event types have been developed. The analytics were tested on 160 signal files and yielded an average accuracy of 99%. Continuous nominal signal data analysis was performed using an approach called the cyclic histogram. The cyclic histogram process is intended to be integrated into the digital fault recorders themselves in order to facilitate the detection of subtle signal variations that are too small to trigger a disturbance event and that can occur over hours or days. In addition to reducing memory requirements by a factor of 320, it is anticipated that cyclic histogram processing will aid in identifying incipient events and identifiers. This project is expected to save engineers time by automating the classification of disturbance events and increasing the reliability of the transmission system by providing near real-time detection and identification of disturbances as well as prevention of problems before they occur.

show abstract

“…With the help of artificial intelligence (AI), data driven methods are also applied to incipient fault detection in power distribution system [16]- [19]. Due to the complex causes and electrical characteristics of incipient faults in power distribution system, it is difficult to establish a comprehensive mathematical model.…”

Section: Introductionmentioning

confidence: 99%

Incipient Fault Detection in Power Distribution System: A Time–Frequency Embedded Deep-Learning-Based Approach

Luo

Cheng

et al. 2023

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Incipient fault detection in power distribution systems is crucial to improve the reliability of the grid. However, the non-stationary nature and the inadequacy of the training dataset due to the self-recovery of the incipient fault signal, make the incipient fault detection in power distribution systems a great challenge. In this paper, we focus on incipient fault detection in power distribution systems and address the above challenges.In particular, we propose an ADaptive Time-Frequency Memory (AD-TFM) cell by embedding wavelet transform into the Long Short-Term Memory (LSTM), to extract features in time and frequency domain from the non-stationary incipient fault signals.We make scale parameters and translation parameters of wavelet transform learnable to adapt to the dynamic input signals.Based on the stacked AD-TFM cells, we design a recurrent neural network with ATtention mechanism, named AD-TFM-AT model, to detect incipient fault with multi-resolution and multi-dimension analysis. In addition, we propose two data augmentation methods, namely phase switching and temporal sliding, to effectively enlarge the training datasets. Experimental results on two open datasets show that our proposed AD-TFM-AT model and data augmentation methods achieve state-of-theart (SOTA) performance of incipient fault detection in power distribution system. We also disclose one used dataset logged at State Grid Corporation of China to facilitate future research.

show abstract

A Synchronized Lissajous-Based Method to Detect and Classify Events in Synchro-Waveform Measurements in Power Distribution Networks

Cited by 21 publications

References 33 publications

Power disturbance waveform analysis and proactive application in power systems

Power disturbance waveform analysis and proactive application in power systems

Learning from Power Signals: An Automated Approach to Electrical Disturbance Identification within a Power Transmission System

Incipient Fault Detection in Power Distribution System: A Time–Frequency Embedded Deep-Learning-Based Approach

Contact Info

Product

Resources

About