A Data Analytic Approach to Automatic Fault Diagnosis and Prognosis for Distribution Automation
read more
Citations
Big data analytics in smart grids: a review
Fault Diagnosis for Energy Internet Using Correlation Processing-Based Convolutional Neural Networks
Fault Location Technology for Power System Based on Information About the Power Internet of Things
A Physical Probabilistic Network Model for Distribution Network Topology Recognition Using Smart Meter Data
References
Visualizing Data using t-SNE
Understanding the difficulty of training deep feedforward neural networks
Case-based reasoning: foundational issues, methodological variations, and system approaches
An efficient k-means clustering algorithm: analysis and implementation
Related Papers (5)
Frequently Asked Questions (15)
Q2. What is the frequent category of fault detected in this particular PMAR?
the Earth Fault and Sensitive Earth Fault (EF/SEF) is the most frequent of the eight categories of fault detected in this particular PMAR.
Q3. What is an example of a protection IED?
A PMAR placed on the overhead lines of a distribution network [14] is an example of a protection IED [15] which combines monitoring and communication capabilities.
Q4. What is the aim of the visualisation of the clusters?
From the visualisation through the t-SNE technique, the aim is to identify one or more specific clusters with the indicative features’ values, which could be used for generate the predictive rules.
Q5. What is the way to check the fault prognosis?
After diagnosing the PMAR device fault and detecting the semi-permanent fault, engineers can also utilise the KBS application to check the fault prognosis report based on the predictive rule developed.
Q6. How many FP groups were derived from this training data set?
A total of 100 FP groups were derived from this training data set and subjected to the data mining process discussed in Section IV.
Q7. How long does the PMAR remain open?
If a reclosure attempt is unsuccessful (indicating the continued presence of a fault) the PMAR device remains open for a period of 10 seconds before attempting a reclose.
Q8. What can be done to help engineers in determining whether a fault exists?
The KBS described in the previous sections can assist control engineers by diagnosing PMAR device faults and identifying potential SPFs present on overhead line circuits.
Q9. How many times does the PMAR attempt to close a fault?
When a fault occurs, the PMAR attempts a set number of reclosure attempts (typically 3 times, as set by the operator in this study).
Q10. What is the process of importing the PMAR log file into the DSS?
After importing the particular PMAR log file, the knowledge–based system will automatically identify PMAR device faults and generate a report through the DSS user interface.
Q11. What is the dimensionality of the clustered data?
To visualise the clustering output from the K-Means algorithm, a dimensionality reduction technique is required to process the clustered data.
Q12. How is the PMAR log file validated?
In order to validate the result of automated diagnosis of PMAR device faults, the original PMAR log file is selected and analysed.
Q13. What is the development process of the KBS?
As shown in Fig. 10, the development of the KBS focuses on deriving and defining the diagnostic and prognostic rules, which are generated through the visualisation and data mining of actual PMAR historical data.
Q14. What can be used to set the thresholds of the rule to predict the TTT?
after filtering this noisy data, the maximum and minimum value of defined features can be used to set the thresholds of the rule to predict the PMAR’s operation.
Q15. How many PMAR log files were used to validate the rule?
REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) <7To validate the rule, 27 unseen PMAR log files containing FP activities and PMAR operations were selected for analysis.