Transmission line fault detection and diagnosis based on fuzzy logic and artificial intelligence

Long-distance power transmission lines are prone to physical faults due to voltage, natural, or other factors. Detecting such faults is automated using modern algorithms with computer-aided features. A Variability-dependent Fault Detection Module (VFDM) is introduced for long-distance grid transmission lines. This module identifies the flow variations and impedance between the transmitting and receiving terminals based on input/output voltage measurements. The categories of flow and their impedance are analyzed for low and high variations to identify the failure or peak transmission using fuzzy logic. The fuzzy process separates the input for impedance and peak transmissions for each voltage cycle. The prediction process due to fluctuations is listed from the failing fuzzy outputs between the low and high variations. By identifying the impedance or flow variations, the successive flaws are predicted using a neural network. The training is pursued independently based on the separated fuzzy inputs. This module is validated using the metrics detection accuracy, impedance rate, and computing time.