A modular neural network approach to fault diagnosis
C Rodriguez1, S Rementeria, J I Martin
1Dept. of Comput., Archit. and Technol., UPV/EHU, Donostia.
IEEE Transactions on Neural Networks
|January 1, 1996
Summary
This study introduces a modular neural network for power system alarm handling and fault diagnosis, overcoming limitations of traditional methods. This scalable and adaptable approach enables accurate identification of single or multiple faults in complex electrical networks.
Area of Science:
- Electrical Engineering
- Artificial Intelligence
- Computer Science
Background:
- Conventional neural network design faces challenges in complex real-world applications.
- Monolithic systems struggle with scalability and dynamic adaptability in power grids.
- Small, fixed-topology networks limit the scope of traditional neural network approaches.
Purpose of the Study:
- To present a modular neural network solution for power systems alarm handling and fault diagnosis.
- To overcome the limitations of conventional, monolithic, and small-scale systems.
- To achieve scalability and dynamic adaptability in fault diagnosis for electrical networks.
Main Methods:
- Developed a modular solution by mapping the power grid onto interconnected modules.
- Modeled the functional behavior of electrical equipment within these modules.
- Employed a competitive hypothesis approach for fault location and diagnosis.
Main Results:
- The modular neural network demonstrated scalability and dynamic adaptability.
- The system effectively handled alarm processing and fault diagnosis in power systems.
- Accurate diagnosis, including simultaneous faults, was achieved.
Conclusions:
- The modular neural network approach offers a flexible and fast solution for power system fault diagnosis.
- This method overcomes the constraints of traditional, monolithic, and small-scale systems.
- The architecture supports natural parallel implementation for enhanced processing.
Related Concept Videos
01:18Fault Types
When analyzing a single line-to-ground fault from phase A to ground at a three-phase bus, it is important to consider the fault impedance. This impedance is zero for a bolted fault, equal to the arc impedance for an arcing fault, and represents the total fault impedance for a transmission-line insulator flashover. To derive sequence and phase currents, fault conditions are translated from the phase domain to the sequence domain.
For line-to-line faults occurring between phases B and C, the...
For line-to-line faults occurring between phases B and C, the...
01:24Bus Impedance Matrix
Calculating subtransient fault currents for three-phase faults in an N-bus power system involves using the positive-sequence network. When a three-phase short circuit occurs at a specific bus, the analysis uses the superposition method to evaluate two separate circuits.
In the first circuit, all machine voltage sources are short-circuited, leaving only the prefault voltage source at the fault location. The positive-sequence bus impedance matrix can be determined by solving the nodal equations,...
In the first circuit, all machine voltage sources are short-circuited, leaving only the prefault voltage source at the fault location. The positive-sequence bus impedance matrix can be determined by solving the nodal equations,...