Dark Mode
Electrical Fault Classification Data
NLP / Natural Language Processing
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset is a collection of line currents and voltages representing various electrical fault conditions within a simulated power system. It is designed to assist in the detection and classification of electrical faults, which are critical for maintaining the stability and reliability of power transmission lines. The modern era's exponential growth in power demand necessitates rapid fault detection and protective equipment operation. This data supports the development of robust protection systems that can quickly identify and classify faults, thereby preventing power outages. The dataset is particularly useful for applying pattern recognition technologies, such as artificial neural networks (ANNs), which are adept at identifying faulty patterns, classifying faults, and distinguishing between healthy and faulty phases in a three-phase power system. ANNs offer excellent normalisation, generalisation capability, immunity to noise, robustness, and fault tolerance in fault detection methods.
Columns
- G: Indicates if a part of the fault line is active (1) or not (0).
- C: Indicates if a part of the fault line is active (1) or not (0).
- B: Indicates if a part of the fault line is active (1) or not (0).
- A: Indicates if a part of the fault line is active (1) or not (0).
- Ia: Line current of phase A.
- Ib: Line current of phase B.
- Ic: Line current of phase C.
- Va: Line voltage of phase A.
- Vb: Line voltage of phase B.
- Vc: Line voltage of phase C.
Distribution
The dataset is provided as a CSV file (
classData.csv), which is 655.03 kB in size. It contains approximately 12,000 data points, with 7,861 valid records for each column, representing measured line voltages and currents under both normal and various fault conditions. The data has been labelled to facilitate classification tasks.Usage
This dataset is ideal for:
- Developing and evaluating machine learning algorithms, particularly artificial neural networks (ANNs), for fault detection and classification in power systems.
- Researching and implementing pattern recognition techniques to discriminate between healthy and faulty electrical power systems.
- Studying the behaviour of three-phase power systems under different fault conditions.
- Designing and testing advanced protection systems for transmission lines that require fast, reliable, and secure relaying operations.
Coverage
The dataset focuses on simulated electrical transient system faults within a power system model. This model includes four generators and transmission lines with transformers, allowing for the study of faults at the midpoint of the transmission line. While no specific geographic or time range is stated, the data is derived from extensive simulations of various fault types.
License
CC0: Public Domain
Who Can Use It
This dataset is suitable for:
- Electrical Engineers: For research into power system protection and fault analysis.
- Machine Learning Researchers: To develop and validate models for anomaly detection and classification in time-series data.
- Academics and Students: For educational purposes, simulating power system dynamics and applying computational intelligence techniques.
- Data Scientists: Interested in real-world application of pattern recognition in critical infrastructure.
Dataset Name Suggestions
- Electrical Fault Classification Data
- Power System Fault Transients
- Transmission Line Faults Dataset
- Grid Fault Analysis Data
- Simulated Electrical Fault Data
Attributes
Original Data Source: Electrical Fault Classification Data
QUALITY