基于新型神经网络分类器的故障诊断模型

摘要

In this paper, a new universial fault instance model is proposed, which aims to solve problems existing in the present technology of fault diagnosis, such as the lack of universality, the difficulty in the use of real time system and the dilemma of stability and plasticity. The FANNC used can settle problems mentioned above by its effectively incremental ability and processing new input patterns via one round learning.%针对故障诊断技术普遍存在的问题：缺乏通用性、不能同时保证稳定性和可塑性以及难以实时应用等，提出了一种故障示例模型，具有较好的通用性；采用的FANNC神经网络具有增量学习能力及只需一遍学习就能完成同新增模式匹配的特点，在保证了模型的实时处理能力的同时，能较好地解决诊断系统的稳定性和可塑性两难问题.故障诊断，神经网络