| 基于神经网络的传感器故障监测与诊断方法研究 |
| |
| 引用本文： | 谷立臣,张优云,丘大谋. 基于神经网络的传感器故障监测与诊断方法研究[J]. 西安交通大学学报, 2002, 36(9): 959-962 |
| |
| 作者姓名： | 谷立臣 张优云 丘大谋 |
| |
| 作者单位： | 西安交通大学润滑理论及轴承研究所,710049,西安 |
| |
| 基金项目： | 国家自然科学基金资助项目(5 9990 4 72 )，国家“九五”攀登B项目(PD95 2 190 8z1) |
| |
| 摘 要： | 提出了一种基于神经网络的传感器故障监测与诊断的新方法。该方法先用BP网络的预测输出和传感器实际输出之差来判断传感器是否发生了故障，然后用函数型连接神经网络模拟传感器的输出特性函数，通过计算神经元连接权值的变化，确定传感器哪个输出特性参数发生了变化，最终推断传感器发生了哪一类故障。该方法的特点是只需要知道一个传感器的信息。电阻应变式力传感器故障诊断实验结果证明了该方法的实用性，为传感器故障监测与诊断提供了一条新途径。
|
| 关 键 词： | 神经网络 传感器 故障监测 输出特性 故障诊断 自适应预测模型 |
| 文章编号： | 0253-987X(2002)09-0959-04 |
| 修稿时间： | 2002-02-26 |
Research on Sensor Failure Detection and DiagnosisBased on Neural Network |
| |
| Gu Lichen,Zhang Youyun,Qiu Damou. Research on Sensor Failure Detection and DiagnosisBased on Neural Network[J]. Journal of Xi'an Jiaotong University, 2002, 36(9): 959-962 |
| |
| Authors: | Gu Lichen Zhang Youyun Qiu Damou |
| |
| Abstract: | A new method for detecting and diagnosing a sensor failure is purposed. A sensor in failure is located through the comparison between the forecast output of back propagation (BP) neural network and the actual one of a sensor. The simulation of sensor output characteristic function with functional link neural network and the calculation of discrepancy of synaptic weight are employed to confirm the changes of an individual output characteristic parameter, and then classifies the failure. This new method needs the signal of one sensor only and has been proved to be unique and practical by the test result of strain sensor failure detection and diagnosis. |
| |
| Keywords: | output characteristic sensor failure neural network detecting and diagnosis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
