摘要
说明了基于神经网络的故障诊断的学习系统的原理,分析了多层感知器的隐层节点数的确定和对BP算法的改进。并以液压泵的故障诊断为例,解释了此学习系统的实现过程。在对BP算法改进之后,系统能很好地实现学习功能,完全达到了预期的结果。
The paper illuminates the principle of learning system in malfunction diagnosis based on neural network , and analyzes how to decide the number of conceal layers node in the multi - sensor and how to improve the BP algorithms, Taking malfunction diagnosis of the fluid pump as an example, it explains the realization process of the learning system. After the improvement of BP algorithms, the system can better realize the learning system, and attain the expected result.
出处
《昆明理工大学学报（理工版）》
2003年第1期39-41,共3页
Journal of Kunming University of Science and Technology(Natural Science Edition)
