Identification (biology)

Electrical engineering

Geology

Pattern recognition (psychology)

Biology

Operating system

Engineering

Arc-fault circuit interrupter

Voltage

Actuator

Time–frequency analysis

Fault detection and isolation

Artificial intelligence

Seismology

Fault (geology)

Capacitive sensing

Computer science

Feature extraction

Botany

Arc (geometry)

Artificial neural network

Radar

Short circuit

Telecommunications

Mechanical engineering

IEEE Transactions on Industrial Informatics

The variety of arc fault induced by different load types makes residential series arc fault detection complicated and challengeable. This paper proposes a hybrid time and frequency analysis and fully connected neural network (HTFNN) based method to identify series ac arc fault. The HTFNN method recognizes samples state by broadly classifying them into resistive (Re) category, capacitive-inductive (CI) category, and switching (Sw) category according to the fundamental frequency components of series current. In each category, separate fully connected neural network (NN) with customized time and frequency indicators being the input is employed for fine class recognition and state identification. This method construction addresses the feature overlap among various cases by separate categories and enables suitable indicator selection within each category. Since the identification complexity in each category is cheaper than identifying all cases together, concise NNs are applied in this paper to reduce computing cost. The general accuracies of normal and arcing state identification in Re, CI, and Sw category are 99.64%, 100%, and 98.45%, respectively, based on 3950 test samples. Method comparison shows that HTFNN achieves higher detection precision at lower computational complexity for generalized load types. This paper also evaluates the feasibility of implementing the method in hardware for arc fault detection device application.

Series AC Arc Fault Detection Method Based on Hybrid Time and Frequency Analysis and Fully Connected Neural Network