Evolutionary Fuzzy ARTMAP Neural Networks and their Applications to Fault Detection and Diagnosis

Abstract

In this paper, two mutation-based evolving artificial neural networks, which are based on the Fuzzy ARTMAP (FAM) network and evolutionary programming, are proposed. The networks utilize the knowledge base extracted from a set of data to perform search and adaptation. The performances of the two networks are assessed using benchmark problems, with the results analyzed and discussed. The effects of the network parameters are evaluated through a parametric study. The applicability of the networks is also demonstrated using a real fault detection and diagnosis task in a power generation plant. The experimental results consistently indicate the usefulness of the proposed evolutionary FAM-based networks in yielding good classification performances with parsimonious network structures.

Harmonic current classification using hybrid FAM-RBF neural network

“…The FAM is capable to overcome stabilityplasticity dilemma and catastrophic forgetting [9][10][11]. Several researches are conducted to enhance the performance of FAM and apply FAM in various application [12][13][14][15][16].…”

A hybrid FAM‐CART model for online data classification

“…4 The main issue of incremental learning is how a learning model can learn new information without forgetting previously learned information. This is also known as the stability-plasticity dilemma, 5,6 which is suffered by most data-based learning models.…”