Fault Diagnosis and Condition Monitoring of Circuit Breakers

Circuit breakers are critical assets in power systems, responsible for interrupting fault currents and ensuring network protection. Fault diagnosis and condition monitoring encompass the detection, classification and prediction of mechanical and electrical anomalies before they lead to failure or unplanned outages. Traditional maintenance relies on scheduled inspections and manual testing, whereas modern approaches favour continuous online surveillance using sensors to capture vibration, current, voltage and partial‐discharge signals. Advanced signal‐processing techniques—such as variational mode decomposition, wavelet analysis and time-frequency entropy—extract salient features from these signals. Machine-learning models, including support vector machines, ensemble classifiers and neural networks, then distinguish normal operation from emerging faults. Challenges in the field include the scarcity of labelled fault data, the diversity of fault modes, environmental noise and the need for real-time diagnosis. Successful implementations have demonstrated reductions in maintenance costs, improved grid reliability and enhanced integration of renewable energy sources.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Fault Diagnosis and Condition Monitoring of Circuit Breakers publication trend

The graph below shows the total number of articles in fault diagnosis and condition monitoring of circuit breakers across all publications each year (not limited to Nature Index journals).

Technical terms

Vibration signal: Mechanical oscillations captured from breaker components during operation, used for analysing mechanical health.

Wavelet packet decomposition: A signal-processing technique that separates a signal into frequency subbands for detailed feature extraction.

Time-frequency entropy: A statistical measure of signal complexity across time and frequency, used to characterise changes in system behaviour.

Support vector machine (SVM): A supervised learning algorithm that classifies data by finding an optimal separating hyperplane in feature space.

Particle swarm optimisation (PSO): A metaheuristic algorithm that iteratively adjusts candidate solutions, inspired by collective behaviour of swarms, for optimizing classifier parameters.

Grey wolf optimisation (GWO): A bio-inspired algorithm simulating grey wolf leadership and hunting strategies to tune parameters in diagnostic models.

References

1. Mechanical Fault Diagnosis of High Voltage Circuit Breakers Based on Variational Mode Decomposition and Multi-Layer Classifier. Sensors (2016).
2. Mechanical Fault Diagnosis of High Voltage Circuit Breakers Based on Wavelet Time-Frequency Entropy and One-Class Support Vector Machine. Entropy (2015).
3. Particle Swarm Optimization-Support Vector Machine Model for Machinery Fault Diagnoses in High-Voltage Circuit Breakers. Chinese Journal of Mechanical Engineering (2020).
4. Fault Diagnosis of Circuit Breaker Energy Storage Mechanism Based on Current-Vibration Entropy Weight Characteristic and Grey Wolf Optimization–Support Vector Machine. IEEE Access (2019).